© 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. 195831
    Prev
    Next
    INDEX
    Explanations

    information

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

    fragmentation, spans, ism, embedding, labels

    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
     deploying
    0.54
    ﻋ
    0.45
    దర్శ
    0.44
     guérison
    0.43
     tách
    0.43
     transporting
    0.43
     Siles
    0.43
    닮
    0.43
     sci
    0.43
     Lyrics
    0.42
    POSITIVE LOGITS
    ,]
    0.52
    RAchievement
    0.51
     familien
    0.50
    Todo
    0.49
    wür
    0.49
    Hasta
    0.49
    kBtu
    0.48
    makarna
    0.48
    leak
    0.47
    valuer
    0.47
    Activations Density 0.001%

    No Known Activations