© 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. 22-GEMMASCOPE-RES-131K
    7. 65424
    Prev
    Next
    INDEX
    Explanations

    bracketed numbers or citations

    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_22/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
     even
    -1.11
     Use
    -0.96
     include
    -0.93
     any
    -0.92
     Kompetenz
    -0.91
     Therefore
    -0.90
     Since
    -0.89
    感覺
    -0.88
    擔任
    -0.88
     so
    -0.86
    POSITIVE LOGITS
     avenir
    0.94
    Ṣ
    0.90
     keren
    0.90
     ciment
    0.89
     plafon
    0.89
     ailes
    0.88
     mobilier
    0.88
    ⑊
    0.87
    佩服
    0.87
     meren
    0.87
    Activations Density 0.024%

    No Known Activations