© 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. 195444
    Prev
    Next
    INDEX
    Explanations

    future bright, failed, sometimes

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

    evaluating Python expressions

    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
    мене
    0.49
    MUL
    0.48
    稈
    0.46
    芢
    0.45
     নিকট
    0.45
     ucc
    0.44
     wymag
    0.44
     wytr
    0.44
     মাকে
    0.44
     požad
    0.44
    POSITIVE LOGITS
    ناس
    0.45
     இய
    0.44
    Initializer
    0.42
     quizá
    0.40
    的故事
    0.40
     initiated
    0.39
    initiated
    0.39
    ۇل
    0.39
    膏
    0.39
    兵
    0.39
    Activations Density 0.000%

    No Known Activations