© 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. 57563
    Prev
    Next
    INDEX
    Explanations

    citations with ref

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

    The neuron fires on tokens that contain digits (i.e. numeric literals or alphanumeric identifiers with 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_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
    fieldType
    -0.73
    FLEX
    -0.72
     bản
    -0.68
    ùn
    -0.67
    compression
    -0.67
    交互
    -0.67
    FieldValue
    -0.65
     Huss
    -0.65
     CEM
    -0.64
    Flu
    -0.63
    POSITIVE LOGITS
    CZ
    0.75
     Preferred
    0.71
    税込
    0.65
     Maine
    0.64
    करण
    0.63
    olian
    0.63
    atoi
    0.63
    PREFERRED
    0.63
    lunda
    0.62
     home
    0.60
    Activations Density 0.094%

    No Known Activations