© 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. 42771
    Prev
    Next
    INDEX
    Explanations

    local neighbourhoods, highest standards

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

    functions and models

    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
    ↵
    0.50
    з
    0.50
    โต
    0.50
    Scottish
    0.50
    ffi
    0.49
    Wisconsin
    0.48
    літ
    0.47
    कई
    0.47
    곱
    0.46
    ิน
    0.46
    POSITIVE LOGITS
    的功能
    0.51
     therapeut
    0.49
    inės
    0.46
    anha
    0.46
     Therapeut
    0.44
    aric
    0.44
     functionally
    0.44
    benzoyl
    0.44
     funcionalidad
    0.44
    wxr
    0.43
    Activations Density 0.001%

    No Known Activations