© 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. 161828
    Prev
    Next
    INDEX
    Explanations

    sledding and tours

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

    Modules vs. modifier or Data Center

    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
    ূত
    0.47
    撕
    0.44
     руководство
    0.43
     Rely
    0.43
     ইঞ্জিন
    0.40
    毫不
    0.39
     Pro
    0.39
    鬥
    0.38
    搅
    0.38
     Theo
    0.38
    POSITIVE LOGITS
    ThoughtData
    0.54
     mantras
    0.54
    ان
    0.53
    Brain
    0.52
     vache
    0.51
    كن
    0.51
    antages
    0.50
    Contacto
    0.50
     Produktion
    0.50
     materialism
    0.49
    Activations Density 0.000%

    No Known Activations