© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34835
    Prev
    Next
    INDEX
    Explanations

    parent references

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

    The neuron flags code‐related tokens—especially programming identifiers (class, method, and variable names) and numeric literals.

    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
     fanns
    -0.99
    thodon
    -0.99
     voltak
    -0.94
    valget
    -0.94
     !}
    -0.92
     {$\
    -0.92
    :'/
    -0.90
    .}\
    -0.90
     when
    -0.89
    ."/
    -0.88
    POSITIVE LOGITS
     between
    0.87
     inhuman
    0.83
    カフェ
    0.82
     skog
    0.82
     Commentaires
    0.81
     چیه
    0.79
    二是
    0.79
     دیگه
    0.79
     dasselbe
    0.77
     اولیه
    0.77
    Activations Density 0.008%

    No Known Activations