© 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. 34-GEMMASCOPE-RES-131K
    7. 65003
    Prev
    Next
    INDEX
    Explanations

    team and experts

    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_34/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
    菇
    -0.81
    |};
    -0.78
    軽減
    -0.76
    幇
    -0.76
    EXCEPT
    -0.74
    リティ
    -0.73
     intram
    -0.73
    Mong
    -0.72
     glú
    -0.72
    遵
    -0.71
    POSITIVE LOGITS
    костюм
    0.79
     of
    0.76
     ešte
    0.74
    ffles
    0.73
     efforts
    0.72
    amel
    0.71
    を
    0.71
    zepam
    0.70
     округ
    0.69
     dedicada
    0.68
    Activations Density 0.024%

    No Known Activations