© 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. 234787
    Prev
    Next
    INDEX
    Explanations

    meaningful stories

    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
    ]，
    0.45
    тік
    0.45
    ometer
    0.44
     バイ
    0.43
     విస్త
    0.43
    étendue
    0.43
    ור
    0.42
    лены
    0.42
    %，
    0.42
     generating
    0.41
    POSITIVE LOGITS
    aggo
    0.42
    add
    0.42
     ইন্দ্র
    0.41
     যেদিন
    0.41
     Cyrus
    0.41
     concreta
    0.41
     daqu
    0.41
     scholarly
    0.40
     Hải
    0.40
    线条
    0.40
    Activations Density 0.000%

    No Known Activations