© 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. 224722
    Prev
    Next
    INDEX
    Explanations

    actions or participation

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

    parameters and capabilities

    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
    どのように
    0.50
    ಿ
    0.49
     hyperbolic
    0.49
     proficiency
    0.48
    дон
    0.46
     comparability
    0.45
    지만
    0.43
     nourishment
    0.42
    ઔ
    0.42
    odesmium
    0.42
    POSITIVE LOGITS
     كلمة
    0.50
     إضافة
    0.47
     Arma
    0.47
     rm
    0.47
     كلمه
    0.47
     &=\
    0.46
     位
    0.46
     ಒಳ್ಳ
    0.46
     herum
    0.46
     =>{
    0.45
    Activations Density 0.000%

    No Known Activations