© 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. 2229
    Prev
    Next
    INDEX
    Explanations

    share and add knowledge

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

    numbers and code delimiters

    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
    烜
    0.37
     Clín
    0.35
    樂
    0.35
    珈
    0.35
    氣
    0.34
    郷
    0.34
     bolog
    0.34
     assayed
    0.33
    SELS
    0.33
    鄕
    0.33
    POSITIVE LOGITS
     />
    0.35
    ":
    0.34
    ></
    0.34
     materialized
    0.33
    };
    0.33
    error
    0.33
    ();
    0.32
    ";
    0.31
    开发者
    0.31
     symbolTable
    0.31
    Activations Density 0.221%

    No Known Activations