© 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. 78634
    Prev
    Next
    INDEX
    Explanations

    period followed by capitalized word

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

    list separators and content

    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
    닝
    0.43
    printDialog
    0.42
     paginate
    0.41
     टक
    0.41
    lessly
    0.40
     recop
    0.40
    мен
    0.40
    redients
    0.40
     instantiated
    0.39
     chiqar
    0.39
    POSITIVE LOGITS
    </em>
    0.43
     Kershaw
    0.41
     गौरतलब
    0.40
    <blockquote>
    0.39
     Edwards
    0.39
     Rib
    0.39
    スカ
    0.39
     สื
    0.38
    Edwards
    0.38
    髅
    0.38
    Activations Density 0.026%

    No Known Activations