© 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. 59506
    Prev
    Next
    INDEX
    Explanations

    numerals and specific names

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

    folksy folk song health reversal AI

    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
    ↵↵
    0.52
     detects
    0.52
    ↵
    0.48
    buds
    0.47
    center
    0.46
    characterized
    0.44
    technology
    0.44
     detected
    0.43
     ,
    0.43
    detected
    0.42
    POSITIVE LOGITS
    玠
    0.54
     автора
    0.53
     చేపట్ట
    0.53
     дизай
    0.51
    泫
    0.50
     Stray
    0.49
     ένα
    0.48
     નિર્ણ
    0.48
     permettre
    0.48
     চেষ্টা
    0.47
    Activations Density 0.000%

    No Known Activations