© 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. 222573
    Prev
    Next
    INDEX
    Explanations

    fittest

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

    degrees Celsius

    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
    t
    0.54
    server
    0.44
    actions
    0.42
    さと
    0.41
    票
    0.41
     javax
    0.41
    新聞
    0.40
    意识
    0.40
    campus
    0.40
    රක
    0.40
    POSITIVE LOGITS
    🕴
    0.49
     לע
    0.48
     Ро
    0.47
     כול
    0.44
    诋
    0.44
     ಕಳೆದ
    0.44
     იყოს
    0.44
     fittest
    0.43
     کشتی
    0.43
     여기서
    0.42
    Activations Density 0.000%

    No Known Activations