© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38898
    Prev
    Next
    INDEX
    Explanations

    reasons/causes (because, since)

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

    The neuron responds to numeric or quantitative expressions (e.g. numbers, decimal values, counts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     those
    -1.25
    -),
    -1.14
    hever
    -1.13
    pecified
    -1.09
    namental
    -1.04
    eping
    -1.04
     with
    -1.04
     after
    -1.03
    cheme
    -1.02
     Tampoco
    -1.01
    POSITIVE LOGITS
     مثل
    1.08
    Our
    1.06
    ことが多い
    1.03
     parfois
    1.02
    Sometimes
    1.00
     dépens
    0.97
    ことがある
    0.97
    anglès
    0.96
    ваги
    0.93
    HasBeenSet
    0.93
    Activations Density 0.073%

    No Known Activations