© 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. 52729
    Prev
    Next
    INDEX
    Explanations

    [ import pickle

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

    common import statements

    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
    <0x0D>
    0.50
    9
    0.40
    on
    0.37
                         
    0.36
    <0x80>
    0.36
    及
    0.36
    8
    0.35
    ad
    0.35
    0.35
    III
    0.35
    POSITIVE LOGITS
     koja
    0.45
     dane
    0.45
     problema
    0.44
     uso
    0.44
     debo
    0.43
     pakai
    0.42
     kasi
    0.42
     renda
    0.42
     usare
    0.41
     lille
    0.41
    Activations Density 0.004%

    No Known Activations