© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 2308
    Prev
    Next
    INDEX
    Explanations

    speaking, listening, writing

    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_all/layer_41_width_262k_l0_big
    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
    <unused1049>
    0.47
    '){
    0.46
     jobNumber
    0.44
    ynomial
    0.43
    xtime
    0.43
    ாவும்
    0.43
     ဖြစ်
    0.42
     ohmic
    0.42
     invertible
    0.42
    的高度
    0.41
    POSITIVE LOGITS
     Speaking
    0.68
     W
    0.63
     Writing
    0.59
     Listen
    0.57
     Listening
    0.56
    W
    0.54
     speaking
    0.52
    Speaking
    0.50
     SL
    0.50
     SPEAK
    0.49
    Activations Density 0.001%

    No Known Activations