© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 218032
    Prev
    Next
    INDEX
    Explanations

    Falling Event

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

    flowering vines, toes, stretching, claw

    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
    Negative Logits
    За
    0.54
    Че
    0.50
    礽
    0.49
    Stranger
    0.49
    丏
    0.48
    Но
    0.47
    Па
    0.47
     savait
    0.47
    してください
    0.47
    +}\
    0.47
    POSITIVE LOGITS
    နှုန်း
    0.49
     enthusiastic
    0.48
    ffen
    0.47
    intention
    0.46
     implied
    0.46
    modulation
    0.44
    mprj
    0.43
    textsc
    0.42
    ekk
    0.42
     ប៉ុ
    0.41
    Activations Density 0.000%

    No Known Activations