© 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. 1076
    Prev
    Next
    INDEX
    Explanations

    technical descriptions or characteristics

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

    word or phrase completion

    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
    ClFN
    0.26
    ংকা
    0.25
     অঞ্জু
    0.25
    聯合
    0.24
     農
    0.24
     डिसेंबर
    0.24
    StarObject
    0.23
    ྕ
    0.23
     पिछली
    0.23
     ইলেক্ট্রো
    0.23
    POSITIVE LOGITS
    的的
    0.37
     it
    0.31
    that
    0.30
    or
    0.29
    to
    0.29
     than
    0.29
    h
    0.29
    ed
    0.29
    하면
    0.29
    in
    0.28
    Activations Density 0.657%

    No Known Activations