© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 62150
    Prev
    Next
    INDEX
    Explanations

    sentence endings

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

    style tags

    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
    )}`;
    0.39
     જેમાં
    0.39
    ạn
    0.37
    دأ
    0.36
    )}.
    0.35
    )}\
    0.35
    癹
    0.35
    nesses
    0.34
    )}}{
    0.34
    ילו
    0.34
    POSITIVE LOGITS
     iris
    0.34
    ോ
    0.32
    指的是
    0.32
    基
    0.31
     factorial
    0.31
    的地方
    0.30
     belong
    0.30
    的是
    0.30
    也不
    0.30
     cadrul
    0.30
    Activations Density 0.000%

    No Known Activations