© 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. 40802
    Prev
    Next
    INDEX
    Explanations

    comma followed by a word

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

    commas followed by potential or choice

    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
    and
    0.78
    which
    0.70
    as
    0.70
     लेकिन
    0.68
    but
    0.66
    а
    0.66
    so
    0.64
    ha
    0.62
    big
    0.60
    not
    0.58
    POSITIVE LOGITS
    ،
    0.67
     vonat
    0.61
     homomorphisms
    0.56
     quelcon
    0.56
     delimiters
    0.55
     morphisms
    0.55
     isotherm
    0.53
     ؟
    0.52
     ovipares
    0.52
     femora
    0.52
    Activations Density 0.074%

    No Known Activations