© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98593
    Prev
    Next
    INDEX
    Explanations

    positions along gradient

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

    The neuron strongly activates on numeric tokens or sequences (e.g. standalone numbers, digits, or numeric literals).

    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
     Flushing
    -0.66
    ريكي
    -0.66
     Frankfurter
    -0.64
    거나
    -0.64
     tribunals
    -0.63
     Franch
    -0.62
    انت
    -0.62
    墳
    -0.62
    YN
    -0.61
     ventri
    -0.61
    POSITIVE LOGITS
     Treasure
    0.71
     corneal
    0.68
    stur
    0.65
    avat
    0.63
    Ⓛ
    0.62
    ᄋ
    0.62
     приведен
    0.62
     пересе
    0.61
     alcan
    0.61
     Pitts
    0.60
    Activations Density 0.084%

    No Known Activations