© 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. 156143
    Prev
    Next
    INDEX
    Explanations

    family time, house, rights

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

    programming and finance terms

    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
     Analysts
    0.52
    }{$\
    0.49
    }']
    0.47
    島
    0.45
    ച്ച
    0.45
     guilds
    0.43
    對方
    0.43
    ^{*}$.
    0.43
     ছাড়াই
    0.42
    }/>
    0.42
    POSITIVE LOGITS
    તે
    0.57
    это
    0.52
    ב
    0.52
    ức
    0.50
    зяй
    0.50
     особенностей
    0.49
    iguez
    0.49
     особенности
    0.49
    ре
    0.49
     ingl
    0.48
    Activations Density 0.000%

    No Known Activations