© 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. 52538
    Prev
    Next
    INDEX
    Explanations

    electrical devices and clusters

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

    describing complexity and efficiency

    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
    <0x80>
    0.57
    3
    0.50
    ла
    0.49
     same
    0.49
    4
    0.49
    ра
    0.49
    {
    0.46
    ت
    0.46
    рой
    0.46
    same
    0.45
    POSITIVE LOGITS
    ᓃ
    0.49
    atthaya
    0.49
     고급
    0.49
    <unused81>
    0.48
    LPTMR
    0.48
     바로
    0.48
     භාවිතා
    0.47
     조직
    0.47
     فبراير
    0.46
     moeil
    0.46
    Activations Density 0.000%

    No Known Activations