© 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. 98919
    Prev
    Next
    INDEX
    Explanations

    older versions and experience

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

    graph concepts or collections

    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
    ヴィ
    0.44
    طانیہ
    0.44
    энд
    0.44
    鮫
    0.44
     казіно
    0.43
    فران
    0.42
     ['./
    0.41
    риб
    0.41
     técnicas
    0.41
    িয়ান
    0.41
    POSITIVE LOGITS
     rust
    0.50
     zwier
    0.50
     graph
    0.43
    l
    0.42
     Graph
    0.41
     Yesterday
    0.41
     Turning
    0.41
     torsion
    0.40
     Сьогодні
    0.40
    🦠
    0.39
    Activations Density 0.001%

    No Known Activations