© 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. 27703
    Prev
    Next
    INDEX
    Explanations

    .

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

    technical examples

    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
     quantidades
    0.43
     filenames
    0.42
    鋏
    0.41
     remit
    0.41
    妗
    0.41
    ברי
    0.40
     fringes
    0.40
    mata
    0.40
     drafts
    0.40
     paintbrush
    0.39
    POSITIVE LOGITS
     écriv
    0.46
    不喜欢
    0.46
    llä
    0.45
     GUIDE
    0.44
     zehn
    0.43
    arpur
    0.41
     během
    0.40
    },"
    0.40
    initState
    0.40
    टॉप
    0.39
    Activations Density 0.000%

    No Known Activations