© 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. 240666
    Prev
    Next
    INDEX
    Explanations

    locations, activities, or states

    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
    हतक
    0.55
    etze
    0.52
     vutto
    0.52
    頩
    0.51
    पयोग
    0.50
    帜
    0.48
    胆
    0.48
     идеи
    0.47
    ጨም
    0.47
     драматур
    0.47
    POSITIVE LOGITS
    /
    0.50
    leftrightarrow
    0.46
     recom
    0.46
    :
    0.45
    ing
    0.44
    frac
    0.44
    ނ
    0.44
    )+\
    0.43
     communes
    0.43
     spectral
    0.43
    Activations Density 0.001%

    No Known Activations