© 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. 26258
    Prev
    Next
    INDEX
    Explanations

    Original Song

    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
    を
    -1.30
    archical
    -1.14
    momix
    -1.11
    ratic
    -1.06
     from
    -1.04
     by
    -0.96
    すべての
    -0.95
    凝土
    -0.95
    erobic
    -0.92
    砲
    -0.92
    POSITIVE LOGITS
    ところに
    1.22
     població
    1.13
    で見る
    1.12
    羕
    1.09
     cabina
    1.09
     Comunic
    1.07
     allowed
    1.06
     occorre
    1.06
     democra
    1.02
     Comuni
    1.02
    Activations Density 0.011%

    No Known Activations