© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 129689
    Prev
    Next
    INDEX
    Explanations

    number and amount

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

    The neuron selectively activates on numeric tokens (e.g. standalone numbers or number‐involving strings).

    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
     a
    -1.60
    佚
    -1.59
    ୬
    -1.55
     taş
    -1.53
    她也
    -1.52
     boundless
    -1.46
     enchanting
    -1.46
    ?”.
    -1.45
    Each
    -1.44
    ailangan
    -1.42
    POSITIVE LOGITS
     who
    2.19
     number
    1.79
    how
    1.71
     många
    1.64
     of
    1.63
     amount
    1.63
    ),
    1.58
     môžete
    1.58
    '
    1.55
     how
    1.50
    Activations Density 0.070%

    No Known Activations