© 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. 7810
    Prev
    Next
    INDEX
    Explanations

    20

    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
    ↵↵
    0.14
    usia
    0.14
    pe
    0.12
    ale
    0.12
    …
    0.12
    ,
    0.11
    ivan
    0.11
    ho
    0.11
    ↵
    0.11
    re
    0.11
    POSITIVE LOGITS
     miljoen
    0.15
    参数
    0.13
    字节
    0.13
     initialise
    0.13
     বৎসর
    0.13
     RetValue
    0.13
    樣本
    0.13
     autorités
    0.12
    系数
    0.12
    视图
    0.12
    Activations Density 0.000%

    No Known Activations