© 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. 81045
    Prev
    Next
    INDEX
    Explanations

    share container broker machine browser periods supply muscles

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

    French and German words

    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
    ο
    0.58
    ின
    0.48
     Hukum
    0.48
    rs
    0.47
    authors
    0.47
    е
    0.46
    и
    0.46
    і
    0.46
    ка
    0.45
    dens
    0.45
    POSITIVE LOGITS
     utilisés
    0.53
     usato
    0.48
     réseaux
    0.47
     arbeit
    0.46
     utk
    0.46
     étudiant
    0.46
     accessoires
    0.46
     attribut
    0.45
    ండ్
    0.45
    Bei
    0.45
    Activations Density 0.000%

    No Known Activations