© 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. 194343
    Prev
    Next
    INDEX
    Explanations

    hunting, computing, and writing subjects

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

    typically explains or defines

    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
    current
    0.46
    value
    0.45
     $\
    0.43
     valutazione
    0.42
    zIndex
    0.42
     experiment
    0.42
    constant
    0.42
     exchange
    0.40
    システムの
    0.40
    HEIGHT
    0.40
    POSITIVE LOGITS
     פור
    0.48
    éges
    0.47
     핸
    0.47
    ರಳ
    0.47
     ని
    0.46
    🔪
    0.46
     நடிக்க
    0.46
     lags
    0.46
     død
    0.46
     сосе
    0.46
    Activations Density 0.000%

    No Known Activations