© 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. 181700
    Prev
    Next
    INDEX
    Explanations

    periodic updates

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

    descriptions of changes and work

    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
     mereka
    0.47
     was
    0.47
     literally
    0.47
     catalyzed
    0.46
     khususnya
    0.46
    ,
    0.45
     zonas
    0.45
     буквально
    0.45
     #{
    0.45
     >>
    0.44
    POSITIVE LOGITS
     نیشنل
    0.47
    sik
    0.44
     मृतकों
    0.43
    nsan
    0.43
    ຝ
    0.43
    falt
    0.42
    onaldo
    0.42
    회가
    0.41
    现在的
    0.41
    国防
    0.41
    Activations Density 0.001%

    No Known Activations