© 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. 112562
    Prev
    Next
    INDEX
    Explanations

    weight sequence, function, initialization, or value

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

    the word "weight" or "weights" in technical and programming 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
    ”
    -2.09
    …
    -1.77
    ."
    -1.61
    i
    -1.56
    ↵↵
    -1.55
    (
    -1.53
    .
    -1.52
    ,”
    -1.45
     Inſ
    -1.41
    근
    -1.41
    POSITIVE LOGITS
     pudieron
    1.86
    
    1.83
    sibilità
    1.75
    僥
    1.71
    д
    1.63
     dieťa
    1.59
     francês
    1.58
    妡
    1.57
     läsa
    1.55
     algunos
    1.55
    Activations Density 0.011%

    No Known Activations