© 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. 77461
    Prev
    Next
    INDEX
    Explanations

    questions followed by what or java

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

    programming imports or uses

    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
    -
    0.54
    via
    0.49
    à
    0.47
    er
    0.46
    Master
    0.45
     David
    0.45
    âng
    0.44
    <h3>
    0.44
    David
    0.44
    ‡
    0.44
    POSITIVE LOGITS
     온도
    0.50
    যানী
    0.44
     저희
    0.44
     flimsy
    0.41
     isother
    0.41
     자기
    0.41
    ඳු
    0.40
     组件
    0.40
     케
    0.40
     ubr
    0.40
    Activations Density 0.000%

    No Known Activations