© 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. 58974
    Prev
    Next
    INDEX
    Explanations

    obtaining results or derivations

    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
    d
    -3.06
    g
    -2.67
    𓋼
    -2.64
    ⽌
    -2.55
    to
    -2.41
    牁
    -2.39
    phans
    -2.33
    wares
    -2.30
    on
    -2.28
    bbling
    -2.28
    POSITIVE LOGITS
    谖
    2.88
     unſ
    2.72
    genodigd
    2.48
    狨
    2.45
    łgorzata
    2.44
    mbgg
    2.41
    詎
    2.41
     dieß
    2.39
    жению
    2.36
    絝
    2.36
    Activations Density 0.001%

    No Known Activations