© 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. 48690
    Prev
    Next
    INDEX
    Explanations

    build system components

    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
    を
    -1.37
    は
    -1.35
     –
    -1.31
    などは
    -1.25
    と
    -1.23
    もしか
    -1.16
    があり
    -1.15
    गर
    -1.15
    などが
    -1.14
     دهید
    -1.13
    POSITIVE LOGITS
    為に
    1.32
     Erstellung
    1.23
    ところに
    1.19
     unido
    1.11
    沕
    1.09
    際は
    1.07
    つづく
    1.07
    &-
    1.07
     ¦
    1.05
     valsty
    1.05
    Activations Density 0.183%

    No Known Activations