© 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. 104095
    Prev
    Next
    INDEX
    Explanations

    degree pertaining to proposal

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

    Gemma family of models

    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
    lipper
    0.44
    Us
    0.42
     killer
    0.41
    killers
    0.41
     Killer
    0.40
    」
    0.39
    များကို
    0.39
     '%'
    0.39
     killers
    0.38
    dash
    0.38
    POSITIVE LOGITS
     ۴
    0.54
    횃
    0.49
     معانا
    0.47
     cena
    0.46
     costruzione
    0.46
    னுடன்
    0.46
    ۴
    0.45
     igra
    0.45
     ottim
    0.45
    InitStruct
    0.44
    Activations Density 0.002%

    No Known Activations