© 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. 63624
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

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

    The neuron strongly activates on numeric tokens—years, match scores, seed numbers, statistics, etc.—i.e. it detects numbers and numerical data.

    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
    itada
    -1.22
     Pemain
    -1.19
     БЕ
    -1.07
     Terbaru
    -1.04
     berjudul
    -1.03
     חשוב
    -1.02
    vaig
    -1.00
    Här
    -0.99
     Проци
    -0.99
    ここでは
    -0.99
    POSITIVE LOGITS
     replaced
    1.57
     also
    1.44
     didn
    1.38
     was
    1.35
     lost
    1.34
     transferred
    1.34
     dropped
    1.27
     switched
    1.20
     died
    1.20
     became
    1.20
    Activations Density 0.049%

    No Known Activations