© 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. 34-GEMMASCOPE-RES-131K
    7. 31675
    Prev
    Next
    INDEX
    Explanations

    problems solved

    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
    んこ
    -1.06
     церемо
    -0.95
     projeto
    -0.94
     deſ
    -0.90
    erving
    -0.90
     debido
    -0.89
    (!__
    -0.87
    "}";
    -0.86
    structed
    -0.84
    苣
    -0.84
    POSITIVE LOGITS
     by
    1.96
     with
    1.76
     satisfactorily
    1.33
     satisfactory
    1.27
     путем
    1.25
     through
    1.20
    就好了
    1.05
     without
    1.04
     bằng
    1.03
     before
    1.02
    Activations Density 0.062%

    No Known Activations