© 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. 22-GEMMASCOPE-RES-131K
    7. 36610
    Prev
    Next
    INDEX
    Explanations

    citations `CR`

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

    The neuron activates on numeric tokens and numeric-like strings (e.g., integers, floating-point numbers, percentages).

    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
     boute
    -0.91
     maillot
    -0.89
    ioli
    -0.88
    硌
    -0.86
     lada
    -0.85
    ³,
    -0.85
     corrom
    -0.84
    μο
    -0.84
     interieur
    -0.83
     too
    -0.82
    POSITIVE LOGITS
     other
    0.88
    ッフ
    0.86
    At
    0.84
     another
    0.79
    bě
    0.77
     At
    0.76
    ッキング
    0.75
    An
    0.74
    Another
    0.74
     at
    0.74
    Activations Density 0.037%

    No Known Activations