© 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. 47418
    Prev
    Next
    INDEX
    Explanations

    listing rankings

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

    into parts or segments

    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
    ”
    0.45
    價格
    0.42
     '#
    0.42
    」
    0.41
     ప్రభుత్వ
    0.41
    irl
    0.39
     ওদের
    0.39
    敕
    0.39
     причем
    0.39
    逮捕
    0.39
    POSITIVE LOGITS
     كيفية
    0.52
     rutina
    0.49
     similaires
    0.49
     bloques
    0.48
     اکت
    0.47
     operativa
    0.47
     kullanılan
    0.47
     accessoires
    0.46
     linéaire
    0.46
     básica
    0.46
    Activations Density 0.000%

    No Known Activations