© 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. 3389
    Prev
    Next
    INDEX
    Explanations

    describing or categorizing items

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

    individual contenders, candidates, types

    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
     vehement
    0.36
     जद
    0.35
     frecuencia
    0.35
     völl
    0.33
     biasa
    0.31
     seguida
    0.31
     ktoś
    0.31
    َم
    0.30
     czym
    0.30
     fois
    0.30
    POSITIVE LOGITS
    案件
    0.37
     contenders
    0.36
    此类
    0.33
     የ
    0.32
    ాలలో
    0.32
     additions
    0.31
     mattresses
    0.31
    这类
    0.31
    Styled
    0.29
    Deze
    0.29
    Activations Density 0.483%

    No Known Activations