© 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. 39144
    Prev
    Next
    INDEX
    Explanations

    offers or provides with free

    np_acts-logits-general · gemini-2.5-flash-lite

    import declarations

    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
    mented
    0.40
    梵
    0.37
    inist
    0.36
     वेळा
    0.36
    萺
    0.36
    }^{-}\
    0.36
     Büro
    0.35
     ثانيه
    0.35
    ical
    0.35
    Simpl
    0.35
    POSITIVE LOGITS
     该
    0.40
     Mould
    0.40
    બર
    0.38
    Hình
    0.37
    omości
    0.37
     שכ
    0.37
     moulded
    0.37
    етки
    0.36
    डमी
    0.36
     histologic
    0.36
    Activations Density 0.004%

    No Known Activations