© 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. 64359
    Prev
    Next
    INDEX
    Explanations

    or ABC

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

    label identifiers

    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
     ряда
    0.44
    認為
    0.41
    ार्थी
    0.40
    RefItem
    0.40
    Detection
    0.40
    羅
    0.39
    Macro
    0.39
    MutableArray
    0.39
    WithObjects
    0.39
    🦒
    0.39
    POSITIVE LOGITS
    imagenes
    0.48
     Mujhe
    0.47
     Neue
    0.46
     електрон
    0.46
     hypert
    0.45
    АН
    0.45
     Maroc
    0.43
     electronic
    0.43
     известный
    0.42
     शिक्
    0.42
    Activations Density 0.000%

    No Known Activations