© 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. 33671
    Prev
    Next
    INDEX
    Explanations

    code comments and separators

    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
    ÓD
    -1.09
     dourada
    -1.05
    uming
    -1.01
     ۸
    -1.00
    翻攝
    -0.98
     napi
    -0.95
    Both
    -0.95
    Pengertian
    -0.93
    bagno
    -0.91
    傚
    -0.90
    POSITIVE LOGITS
    ;">
    1.04
    deoxy
    0.92
     Oates
    0.88
     собственности
    0.86
    ánk
    0.86
     Involvement
    0.85
    乃
    0.85
     blamed
    0.84
     pihaknya
    0.84
    iciado
    0.84
    Activations Density 0.000%

    No Known Activations