© 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. 121667
    Prev
    Next
    INDEX
    Explanations

    scoring on, with recipes, for expert

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

    history, current status, and breakdown

    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
    품
    0.53
    Người
    0.51
    供應
    0.48
    بر
    0.47
    ᱟ
    0.47
    SUP
    0.46
    懸
    0.46
    ουσ
    0.45
    僞
    0.45
    說
    0.45
    POSITIVE LOGITS
     executed
    0.55
     courteous
    0.54
     experiments
    0.52
     islets
    0.52
     notations
    0.52
     accorded
    0.52
     policewomen
    0.52
     पॉलिटी
    0.50
     sanguine
    0.50
     battalion
    0.50
    Activations Density 0.000%

    No Known Activations