© 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. 160638
    Prev
    Next
    INDEX
    Explanations

    web page, new service, prize itself

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

    (Chorus)

    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
    кан
    0.57
    ал
    0.57
     computerChoice
    0.54
     부탁
    0.53
     tathapi
    0.52
     방송
    0.52
     साक्षी
    0.51
     옳
    0.50
    ат
    0.50
     непро
    0.50
    POSITIVE LOGITS
     is
    0.58
    '
    0.53
    <start_of_image>
    0.52
    \
    0.51
    Sites
    0.50
    0.50
     of
    0.48
    Rows
    0.46
     minimum
    0.45
     with
    0.45
    Activations Density 0.000%

    No Known Activations