© 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. 158502
    Prev
    Next
    INDEX
    Explanations

    discuss with

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

    context" or log"

    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
     فا
    0.50
    ುಕ
    0.48
     дале
    0.48
     niezb
    0.46
     مما
    0.44
     aast
    0.44
     ਨ
    0.44
    舗
    0.44
     بأ
    0.44
    ніза
    0.44
    POSITIVE LOGITS
    times
    0.49
    erti
    0.47
    can
    0.47
    tes
    0.46
    anj
    0.46
     wirelessly
    0.46
    fx
    0.45
    iremos
    0.44
    \
    0.44
    ’
    0.44
    Activations Density 0.000%

    No Known Activations