© 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. 173519
    Prev
    Next
    INDEX
    Explanations

    open documentation

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

    practical information requests

    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
     स्टेन
    0.52
    籮
    0.50
    糾
    0.47
     Guelph
    0.45
     বলব
    0.44
    branes
    0.44
    مث
    0.44
     mortars
    0.44
     Moroccan
    0.44
     Staples
    0.44
    POSITIVE LOGITS
    은
    0.50
     为了
    0.48
    addChild
    0.47
    运用
    0.47
     straks
    0.46
    iré
    0.46
    ù
    0.45
     ต้อง
    0.44
    东西
    0.44
    迟
    0.44
    Activations Density 0.000%

    No Known Activations