© 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. 66046
    Prev
    Next
    INDEX
    Explanations

    http links or addresses

    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
    VertexAttrib
    -1.20
    TestBed
    -1.16
    fordshire
    -1.08
     maleta
    -1.06
     MessageBoxIcon
    -1.04
     doigt
    -1.04
     =>
    -1.03
     Partido
    -1.03
     także
    -1.02
    etration
    -1.02
    POSITIVE LOGITS
    '
    0.98
     betreff
    0.97
    sobí
    0.96
    也就是说
    0.94
    民宿
    0.94
    唷
    0.93
     darstellen
    0.93
     zulassen
    0.90
    ↵↵
    0.89
     halb
    0.88
    Activations Density 0.004%

    No Known Activations