© 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. 15530
    Prev
    Next
    INDEX
    Explanations

    Q: followed by numbers

    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
    がよく
    -1.01
     trés
    -0.96
    weitere
    -0.95
     that
    -0.95
     armé
    -0.94
    pneu
    -0.93
    furter
    -0.93
    эти
    -0.93
     még
    -0.90
    dhury
    -0.90
    POSITIVE LOGITS
    日常
    0.94
    汉
    0.94
    最初
    0.91
    ösungen
    0.91
    レイ
    0.88
     tans
    0.86
     beneficial
    0.85
     facil
    0.84
     ningún
    0.84
    MAN
    0.82
    Activations Density 0.004%

    No Known Activations