© 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. 32711
    Prev
    Next
    INDEX
    Explanations

    reading time in minutes and pages

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

    estimated duration or page count

    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
    ocommerce
    0.50
     oficina
    0.47
    osaic
    0.45
     ))->
    0.44
    tDBOutput
    0.43
     ವಿವಿಧ
    0.42
     ሁሉም
    0.42
     popis
    0.41
     iner
    0.41
    Workshop
    0.41
    POSITIVE LOGITS
    唠
    0.42
     approximated
    0.39
     contractions
    0.39
     Env
    0.37
    .
    0.37
    .~
    0.37
     equated
    0.36
    lede
    0.36
    엄
    0.36
     이어
    0.36
    Activations Density 0.001%

    No Known Activations