© 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. 112979
    Prev
    Next
    INDEX
    Explanations

    broaden view

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

    broaden your view

    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
    ğından
    0.52
    нар
    0.51
    мещение
    0.51
    న్యూ
    0.49
    ਰਾ
    0.49
    शाही
    0.49
    गेट
    0.48
    ղ
    0.47
    ᱦ
    0.47
    ган
    0.47
    POSITIVE LOGITS
     broaden
    0.50
     świata
    0.47
     widen
    0.45
     緑
    0.43
     ('
    0.43
     deficit
    0.42
     See
    0.41
     Broad
    0.41
     všech
    0.41
     view
    0.41
    Activations Density 0.000%

    No Known Activations