© 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. 22-GEMMASCOPE-RES-131K
    7. 25737
    Prev
    Next
    INDEX
    Explanations

    accessing object members via dot

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

    The neuron activates on numeric literal tokens (digits) in code.

    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
     them
    -1.67
    Kanpo
    -1.30
     którzy
    -1.21
     They
    -1.16
    >-</
    -1.12
    だよね
    -1.11
    ઃ
    -1.11
     that
    -1.09
    谟
    -1.09
    -};
    -1.07
    POSITIVE LOGITS
    '
    1.11
    ⎟
    1.09
    ói
    1.08
     INSTANCE
    1.06
    *
    1.05
    -
    1.04
     Camo
    1.01
     determinados
    1.01
    .
    1.01
     was
    0.97
    Activations Density 0.006%

    No Known Activations