© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7874
    Prev
    Next
    INDEX
    Explanations

    verbs followed by prepositions or auxiliaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -2.08
     is
    -1.86
     where
    -1.80
     itself
    -1.80
     or
    -1.71
    或
    -1.63
    ⤵
    -1.55
     how
    -1.54
     has
    -1.53
    ichtete
    -1.53
    POSITIVE LOGITS
     themselves
    1.93
     แต่
    1.73
    疃
    1.73
     لكن
    1.61
    たまに
    1.55
    凄く
    1.55
    ").
    1.53
    ⑊
    1.53
    película
    1.45
    を見つけ
    1.45
    Activations Density 0.065%

    No Known Activations