© 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. 89433
    Prev
    Next
    INDEX
    Explanations

    download or browse

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

    not just a

    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
    CACHE
    0.46
    Scientific
    0.46
    FOOD
    0.45
     PA
    0.44
    AMAN
    0.44
     loosing
    0.43
     ");
    0.41
    様に
    0.41
    Lf
    0.41
    Auf
    0.41
    POSITIVE LOGITS
     răm
    0.48
    ंख्य
    0.46
    撐
    0.45
    寥
    0.45
     distinta
    0.45
    ütter
    0.45
    اتھن
    0.44
    шинство
    0.43
     المتح
    0.43
    ंगामा
    0.43
    Activations Density 0.000%

    No Known Activations