© 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. 50120
    Prev
    Next
    INDEX
    Explanations

    language and traditions

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

    being named

    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
     Garry
    0.54
    aque
    0.49
    dz
    0.48
    নীর
    0.48
     Mahmood
    0.48
     Zhan
    0.47
    guez
    0.46
    z
    0.46
    gres
    0.45
     জনসাধারণ
    0.45
    POSITIVE LOGITS
    </h3>
    0.55
    ↵↵
    0.54
    </i>
    0.50
     convince
    0.46
     мя
    0.45
    <h3>
    0.45
    ला
    0.44
     Ваши
    0.44
     adventures
    0.44
    出手
    0.43
    Activations Density 0.000%

    No Known Activations