© 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. 148314
    Prev
    Next
    INDEX
    Explanations

    lists, culture, and values

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

    leading to

    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
     folgen
    0.54
     kursi
    0.46
     combinations
    0.46
     ამ
    0.46
    ဆ
    0.45
     manj
    0.44
    0.44
     لی
    0.44
     רא
    0.44
    არა
    0.44
    POSITIVE LOGITS
    🏮
    0.46
    umā
    0.45
    Numerical
    0.44
     Numerical
    0.44
     गतिविधियों
    0.43
    inį
    0.43
    ளிலும்
    0.42
     निवेशकों
    0.41
    getProduct
    0.41
    smoke
    0.41
    Activations Density 0.001%

    No Known Activations