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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30297
    Prev
    Next
    INDEX
    Explanations

    contrasting scales

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

    The neuron activates on words that specify quantitative measures or magnitudes—numerical descriptors, scales, sizes, or degree qualifiers.

    oai_token-act-pair · o4-miniTriggered 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
     préciser
    -0.84
    pte
    -0.83
    due
    -0.81
     entram
    -0.80
    lil
    -0.78
     Epsilon
    -0.76
    idées
    -0.74
     Datum
    -0.71
     Ê
    -0.71
     meest
    -0.71
    POSITIVE LOGITS
     values
    1.09
     but
    0.94
     enough
    0.90
     separation
    0.88
     regions
    0.85
     Compared
    0.83
     changes
    0.82
    носить
    0.82
     systems
    0.82
    -|
    0.81
    Activations Density 0.054%

    No Known Activations