© 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. 87951
    Prev
    Next
    INDEX
    Explanations

    sensing waterfalls

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

    understanding and definitions

    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
     ஆன்
    0.58
     ช่อง
    0.57
     अशी
    0.56
     समुद्री
    0.55
     গ
    0.55
     MONTH
    0.54
     गर्व
    0.53
     ਗ
    0.52
     ആഘോഷ
    0.52
     화학
    0.52
    POSITIVE LOGITS
    i
    0.58
    рни
    0.49
    ﺬ
    0.46
    лли
    0.46
    хова
    0.45
    o
    0.44
    翠
    0.44
    can
    0.43
    кции
    0.43
    h
    0.42
    Activations Density 0.000%

    No Known Activations