© 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. 247707
    Prev
    Next
    INDEX
    Explanations

    cut short

    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
    despite
    0.50
     despite
    0.47
    Despite
    0.46
     Despite
    0.46
    preferably
    0.45
    綸
    0.44
    )_
    0.43
    UNA
    0.43
    EP
    0.43
    Ø
    0.43
    POSITIVE LOGITS
    cleaning
    0.61
     cleaning
    0.54
    维修
    0.52
     nettoyage
    0.52
    保养
    0.52
    趼
    0.52
    ávat
    0.50
     убор
    0.49
    पंचायत
    0.48
    rick
    0.48
    Activations Density 0.000%

    No Known Activations