© 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. 129074
    Prev
    Next
    INDEX
    Explanations

    published by

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

    concise synopsis or description

    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
     Assessing
    0.46
     Toxicology
    0.42
     বারবার
    0.41
     ("",
    0.41
    嵌套
    0.40
     [\
    0.40
     $-\
    0.40
    ,|\
    0.39
     छह
    0.39
     Virology
    0.39
    POSITIVE LOGITS
    ysł
    0.47
    égal
    0.47
    aced
    0.46
    emor
    0.46
    और
    0.46
     प्रताप
    0.46
    ЕР
    0.46
    などが
    0.46
    wane
    0.45
    आर
    0.45
    Activations Density 0.001%

    No Known Activations