© 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. 7166
    Prev
    Next
    INDEX
    Explanations

    business and its operations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     vistas
    -1.74
     peix
    -1.57
     verhalen
    -1.57
    här
    -1.56
     mariée
    -1.54
    튿
    -1.54
    虓
    -1.44
    空白
    -1.43
    ֊
    -1.43
    푘
    -1.40
    POSITIVE LOGITS
    k
    1.73
    f
    1.69
    in
    1.68
    0
    1.66
    g
    1.65
    business
    1.63
    from
    1.63
    s
    1.58
    ce
    1.55
    ts
    1.55
    Activations Density 0.050%

    No Known Activations