© 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. 10-GEMMASCOPE-RES-131K
    7. 102478
    Prev
    Next
    INDEX
    Explanations

    prod followed by script or colon

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

    the word "prod" as a prefix or standalone token, particularly in technical and code contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ladolid
    -2.67
    ⬮
    -2.52
     ‚
    -2.42
    uttori
    -2.42
     valentín
    -2.39
    凩
    -2.36
    遄
    -2.36
     pointless
    -2.31
     πιο
    -2.25
    
    -2.19
    POSITIVE LOGITS
    the
    2.94
    t
    2.73
    2
    2.63
    他們
    2.56
    進入
    2.55
    If
    2.53
    1
    2.50
    鄒
    2.42
    When
    2.42
    ting
    2.38
    Activations Density 0.002%

    No Known Activations