© 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. 8118
    Prev
    Next
    INDEX
    Explanations

    talking to or heat

    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
    Bechyné
    0.39
    उदा
    0.35
    บน
    0.31
     सिफारिश
    0.31
     अधिकतम
    0.31
     देशा
    0.31
     elution
    0.31
    <unused82>
    0.31
    र्दू
    0.30
    SXml
    0.30
    POSITIVE LOGITS
     and
    0.39
    ’
    0.36
     or
    0.35
    [
    0.34
    ↵
    0.34
     If
    0.34
    ).
    0.33
     [
    0.33
    .
    0.33
    В
    0.33
    Activations Density 0.001%

    No Known Activations