© 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. 62472
    Prev
    Next
    INDEX
    Explanations

    tokens following punctuation or conjunctions

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

    activities, tasks, and completion

    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
     與
    0.50
     QSOs
    0.48
     Lenin
    0.47
     Тимо
    0.46
     あれ
    0.45
     yourselves
    0.44
     др
    0.44
     melanch
    0.44
     *)
    0.44
     composers
    0.44
    POSITIVE LOGITS
    itching
    0.51
     it
    0.47
     they
    0.46
    이죠
    0.45
    首次
    0.44
     දි
    0.43
    elo
    0.43
    谪
    0.43
    ihat
    0.42
     busting
    0.42
    Activations Density 0.000%

    No Known Activations