© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 260412
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    诤
    0.41
    রাতে
    0.39
     Exile
    0.37
     оружи
    0.37
     archive
    0.37
     exile
    0.36
     Canine
    0.36
     అదే
    0.36
    FAF
    0.35
     रहकर
    0.35
    POSITIVE LOGITS
     られ
    0.50
    SpriteCollision
    0.50
    ander
    0.48
    ナトリ
    0.47
    mals
    0.47
    ഃ
    0.46
    hibit
    0.46
     partecipazione
    0.46
    ệu
    0.45
     figura
    0.45
    Activations Density 0.000%

    No Known Activations