© 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. 104041
    Prev
    Next
    INDEX
    Explanations

    accept it as

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

    breaking down complexities

    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
    推荐
    0.43
    酰
    0.42
    inand
    0.42
     robustness
    0.42
    ερμαν
    0.41
    วด
    0.41
    RO
    0.40
     recouvert
    0.40
    傥
    0.40
     dáng
    0.40
    POSITIVE LOGITS
     ત્યાર
    0.46
     عارفين
    0.46
     Afterwards
    0.45
    箓
    0.45
    സ്ഥാന
    0.44
     سکتے
    0.44
    𝖘
    0.43
    जत
    0.42
     Daarna
    0.42
     исходя
    0.42
    Activations Density 0.000%

    No Known Activations