© 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. 163885
    Prev
    Next
    INDEX
    Explanations

    specific situations or entities

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

    reducing or comparing options

    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
    AA
    0.49
    ıları
    0.49
    Pas
    0.47
    5
    0.46
    bets
    0.45
    ת
    0.44
    ILTON
    0.43
    <thead>
    0.43
    纯
    0.42
    <ul>
    0.42
    POSITIVE LOGITS
     cambiando
    0.52
     혹은
    0.51
     Bombardier
    0.51
     horsepower
    0.50
     passenger
    0.50
     لاکھ
    0.49
     bruit
    0.49
     jaguar
    0.48
     enduro
    0.48
     Lamborghini
    0.47
    Activations Density 0.000%

    No Known Activations