© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113847
    Prev
    Next
    INDEX
    Explanations

    Completion of an action

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

    done followed by function call or punctuation

    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
    olič
    0.48
    Scroll
    0.46
     রুম
    0.44
    Argument
    0.43
    ettivi
    0.43
    ]}$
    0.43
     কথাটা
    0.42
    ৭০
    0.42
     اكتب
    0.42
    <>
    0.41
    POSITIVE LOGITS
     done
    0.57
     Done
    0.55
    Done
    0.55
     dilakukan
    0.50
    全く
    0.47
     gone
    0.47
     gedaan
    0.47
     Gone
    0.47
     xong
    0.47
    સ્તુ
    0.46
    Activations Density 0.070%

    No Known Activations