© 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. 211329
    Prev
    Next
    INDEX
    Explanations

    days and specific events

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

    contrast and correction

    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
    तों
    0.45
     périphérique
    0.44
    год
    0.44
    $}
    0.43
    ymax
    0.42
    $&
    0.42
    дает
    0.42
    }$&
    0.42
    IELD
    0.42
    PointSize
    0.42
    POSITIVE LOGITS
     inflamed
    0.47
     variously
    0.47
    etzte
    0.43
    ాల్సి
    0.43
     जानेवारी
    0.42
    esimo
    0.42
     Ashley
    0.41
     necesitas
    0.41
     leit
    0.41
    。《
    0.41
    Activations Density 0.001%

    No Known Activations