© 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. 64678
    Prev
    Next
    INDEX
    Explanations

    instructions and advice

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    મ
    0.49
    States
    0.44
    АР
    0.44
    HINSTANCE
    0.43
    }--
    0.42
    ul
    0.41
    НА
    0.41
    ર
    0.41
    {~
    0.40
    sembling
    0.40
    POSITIVE LOGITS
    のではなく
    0.49
     koska
    0.46
     laag
    0.46
     क्योंकि
    0.45
     diferentes
    0.45
     különböző
    0.44
     çünkü
    0.44
     conversación
    0.44
     eftersom
    0.43
     kolor
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.