© 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. 110302
    Prev
    Next
    INDEX
    Explanations

    color schemes, sprout, ingredients

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

    historical data analysis

    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
     prosec
    0.51
     striis
    0.48
     جیتنے
    0.45
     डेविड
    0.44
     DAVID
    0.44
    삵
    0.44
     foliis
    0.44
    기로
    0.44
    ंसक
    0.44
     pounds
    0.43
    POSITIVE LOGITS
     শাও
    0.47
    াড়া
    0.47
    О
    0.47
    layout
    0.46
    emplacement
    0.45
    renown
    0.45
    do
    0.44
    eh
    0.44
    detail
    0.44
    kj
    0.44
    Activations Density 0.003%

    No Known Activations