© 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. 173260
    Prev
    Next
    INDEX
    Explanations

    signing and providing information

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

    database systems

    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
    까
    0.42
    V
    0.41
    )+(
    0.40
    ptid
    0.40
     ہوج
    0.39
    MATERIAL
    0.39
     fervent
    0.39
    uhi
    0.39
    大哥
    0.39
    ರುವುದರಿಂದ
    0.39
    POSITIVE LOGITS
     kolejne
    0.52
     contextual
    0.51
     মনোনীত
    0.50
     болезнь
    0.50
     евре
    0.48
     podstaw
    0.47
    🐭
    0.47
     celebrated
    0.46
    签署
    0.45
     প্রদান
    0.44
    Activations Density 0.001%

    No Known Activations