© 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. 125192
    Prev
    Next
    INDEX
    Explanations

    viral music

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

    anime generation, code, results

    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
     ц
    0.46
     arrays
    0.46
    чення
    0.46
     хранения
    0.46
     rearrangements
    0.46
    EVENT
    0.45
    DQ
    0.45
    _
    0.44
     événement
    0.44
     snapshots
    0.44
    POSITIVE LOGITS
     في
    0.54
     Erste
    0.52
     国家
    0.48
     पैसा
    0.48
     गाली
    0.47
    gie
    0.46
     diseño
    0.45
     Cardi
    0.45
     Koran
    0.45
     Money
    0.44
    Activations Density 0.000%

    No Known Activations