© 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. 9609
    Prev
    Next
    INDEX
    Explanations

    numbers following conjunctions

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

    figure out

    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
     disagree
    0.46
    leman
    0.46
     mechan
    0.46
    ^{*}
    0.46
     gentamicin
    0.45
    hiti
    0.45
     DICE
    0.44
     Cowan
    0.44
     vocals
    0.43
     inconvenience
    0.43
    POSITIVE LOGITS
    創建
    0.52
    會員
    0.50
    澱
    0.50
    Creating
    0.45
     میلیون
    0.45
     створення
    0.44
    فاعل
    0.44
     သူ့
    0.42
    ごはん
    0.42
     criando
    0.42
    Activations Density 0.000%

    No Known Activations