© 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. 55776
    Prev
    Next
    INDEX
    Explanations

    describing state or status

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

    lists of collected things

    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
     千
    0.47
     TOKEN
    0.47
    千
    0.46
     outbound
    0.44
     glBind
    0.43
    飚
    0.42
     横
    0.42
    なかった
    0.41
     elu
    0.41
    欉
    0.41
    POSITIVE LOGITS
    Lady
    0.50
    परेशन
    0.47
    Newswire
    0.47
    are
    0.46
    etl
    0.46
    reach
    0.46
    гов
    0.46
     செய்யப்பட்டது
    0.46
    ov
    0.44
    arranged
    0.44
    Activations Density 0.000%

    No Known Activations