© 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. 142856
    Prev
    Next
    INDEX
    Explanations

    languages, words, organizations, things

    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
     ခ
    0.39
     Cholesterol
    0.39
     λ
    0.38
     Oil
    0.38
     অবস্থা
    0.37
     执行
    0.36
    ;|
    0.36
     రెండో
    0.35
     Least
    0.35
     Lesser
    0.35
    POSITIVE LOGITS
    Evet
    0.52
    agonist
    0.52
     socialista
    0.49
     janu
    0.49
    Вели
    0.48
    encion
    0.48
    ᠬ
    0.48
    Тре
    0.47
    serie
    0.46
    raison
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.