© 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. 41628
    Prev
    Next
    INDEX
    Explanations

    It seems

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

    Market Size

    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
    嘏
    0.50
     novedades
    0.49
    薨
    0.49
    谆
    0.48
    ರ್ಮ
    0.48
     enfermed
    0.46
     armazenamento
    0.46
    스를
    0.46
    ك
    0.46
    Chevrolet
    0.46
    POSITIVE LOGITS
     しっかり
    0.47
     (
    0.45
    itage
    0.41
     DIY
    0.41
    kiy
    0.41
    しっかりと
    0.40
    clude
    0.40
     แถม
    0.39
    /
    0.39
     デザイン
    0.38
    Activations Density 0.000%

    No Known Activations