© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 12026
    Prev
    Next
    INDEX
    Explanations

    change with

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on words indicating quantitative change or trend (e.g. increases, decreases, gradually increased).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    words indicating an increase or upward change in scientific or technical measurements.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    statements describing quantitative or directional changes, such as increases, decreases, gradual trends, and gradients in variables.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    بدون
    -1.01
     maniere
    -0.91
     heilig
    -0.85
     leher
    -0.85
     seksi
    -0.84
     gâ
    -0.84
     Pantry
    -0.83
     minimalis
    -0.82
     novamente
    -0.82
    hrungen
    -0.82
    POSITIVE LOGITS
     with
    3.08
    随着
    2.42
     as
    2.27
    隨著
    2.11
     when
    1.99
     wraz
    1.88
     upon
    1.73
     With
    1.67
     along
    1.67
    With
    1.42
    Activations Density 0.200%

    No Known Activations