© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 193188
    Prev
    Next
    INDEX
    Explanations

    tips, credit, lagoon, luggage

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

    recently transcribed SRT files

    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
    бр
    0.47
     χρήση
    0.47
    рд
    0.43
    为什么要
    0.43
    ις
    0.43
    te
    0.43
    кая
    0.43
    к
    0.43
    ६
    0.42
    °)
    0.42
    POSITIVE LOGITS
    るので
    0.50
     Lagoon
    0.49
    पदी
    0.48
     lagoon
    0.48
     عاوز
    0.47
     relocate
    0.46
     lake
    0.46
    edDevice
    0.46
     piece
    0.46
     mezcla
    0.45
    Activations Density 0.001%

    No Known Activations