© 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. 102326
    Prev
    Next
    INDEX
    Explanations

    reference for

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

    force translates

    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
     thisobject
    0.57
     오른
    0.55
    닌
    0.51
     obstacles
    0.51
     roadblocks
    0.50
    
    0.50
    ２
    0.50
     volonté
    0.49
    <unused1129>
    0.49
     Apar
    0.49
    POSITIVE LOGITS
    gif
    0.44
    getchar
    0.43
     detect
    0.43
    driver
    0.42
     ي
    0.42
    after
    0.41
    Verify
    0.40
     वही
    0.40
    ย
    0.40
    识别
    0.40
    Activations Density 0.000%

    No Known Activations