© 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. 10-GEMMASCOPE-RES-131K
    7. 60899
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and sequences

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

    The neuron responds primarily to tokens representing numerical values (digits and numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ᨆ
    -2.19
    榈
    -2.09
    騭
    -2.08
     raiſ
    -2.05
     promove
    -1.95
    螃
    -1.91
    鹩
    -1.91
     grotte
    -1.91
     licorne
    -1.90
     veau
    -1.89
    POSITIVE LOGITS
     and
    2.36
    ).
    2.31
    ?
    2.14
    。
    2.09
    {
    2.06
    ↵↵↵
    1.91
    There
    1.88
    …
    1.86
     we
    1.84
    For
    1.84
    Activations Density 0.812%

    No Known Activations