© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135991
    Prev
    Next
    INDEX
    Explanations

    current date/time availability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Europeo
    0.50
     inherent
    0.44
     activos
    0.42
    <0xD0>
    0.42
     mischiev
    0.42
     actifs
    0.41
     imprensa
    0.41
     blissful
    0.41
    কাতার
    0.40
    يت
    0.40
    POSITIVE LOGITS
    </h3>
    0.48
     কাজ
    0.48
    ם
    0.47
    sling
    0.46
    elics
    0.46
    s
    0.46
    utation
    0.46
    lovi
    0.46
    ⬅
    0.44
     પ્રકાશ
    0.44
    Activations Density 0.003%

    No Known Activations