© 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. 22930
    Prev
    Next
    INDEX
    Explanations

    making plans to organize

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

    by critically

    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
    ພວກເຮົາ
    0.37
    ানিতে
    0.37
    所谓
    0.36
     흰
    0.35
     murdering
    0.35
    (`${
    0.35
    흰
    0.34
    យើង
    0.33
    ພວກເຮ
    0.33
    यदि
    0.32
    POSITIVE LOGITS
     compless
    0.43
    ﺠ
    0.37
     ܠ
    0.35
     reak
    0.34
    <0xCD>
    0.34
     szé
    0.34
    கால
    0.34
     zároveň
    0.33
     デ
    0.32
    భ
    0.32
    Activations Density 0.000%

    No Known Activations