© 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. 111429
    Prev
    Next
    INDEX
    Explanations

    helps reduce

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

    tax, fat, life, receptors

    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
    h
    0.56
    hose
    0.48
    an
    0.48
    hmen
    0.48
    x
    0.48
    sp
    0.46
    hin
    0.46
    hese
    0.46
    ící
    0.45
    Б
    0.44
    POSITIVE LOGITS
     Wim
    0.56
     NADPH
    0.51
     Afric
    0.50
     Dien
    0.50
     Só
    0.48
     Babel
    0.48
     Dier
    0.47
     François
    0.47
     歴史
    0.47
     Gink
    0.47
    Activations Density 0.000%

    No Known Activations