© 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. 31984
    Prev
    Next
    INDEX
    Explanations

    prevent income, full recovery, user interests

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

    basic version or client-side JavaScript

    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
     altra
    0.49
     我的
    0.48
     siguiente
    0.45
     ปุ่ม
    0.45
    镤
    0.45
    ب
    0.45
    codewords
    0.44
    engaruhi
    0.44
     otro
    0.43
     extrémité
    0.43
    POSITIVE LOGITS
    rio
    0.46
    規劃
    0.42
    েশনে
    0.41
    悖
    0.41
     Hamm
    0.41
    isesti
    0.41
     Moll
    0.40
     outweighed
    0.40
    蛻
    0.40
    ’.”
    0.39
    Activations Density 0.000%

    No Known Activations