© 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. 47575
    Prev
    Next
    INDEX
    Explanations

    n as a number

    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
    যখন
    0.45
    ि
    0.43
    後的
    0.43
    ки
    0.42
    𝜆
    0.41
    㝢
    0.41
     দুর্ভিক্ষের
    0.40
    實際
    0.40
    相對
    0.40
     +=
    0.39
    POSITIVE LOGITS
    वासियों
    0.47
    니스
    0.46
     Quatre
    0.44
    ەی
    0.43
     Maschine
    0.42
     douze
    0.41
     Découvrez
    0.41
    ച്ചി
    0.39
     Kazim
    0.39
     Lac
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.