© 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. 65945
    Prev
    Next
    INDEX
    Explanations

    finding attributes or properties

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

    The neuron fires on relatively long alphanumeric tokens (e.g. identifiers or multi-syllable words) in code or comments.

    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
     plafond
    -0.98
     eaux
    -0.93
    >(</
    -0.89
     Wiktionnaire
    -0.89
     patro
    -0.87
    ség
    -0.85
     FAITH
    -0.84
    ЕРЕ
    -0.84
     abonnement
    -0.84
    が変わ
    -0.82
    POSITIVE LOGITS
     nestled
    1.10
     exquisite
    1.04
     before
    0.98
    Most
    0.98
     exquisitely
    0.96
    Despite
    0.95
     came
    0.95
    If
    0.95
     brilliant
    0.95
     took
    0.94
    Activations Density 0.020%

    No Known Activations