© 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. 213217
    Prev
    Next
    INDEX
    Explanations

    operational tasks and management

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

    rhythmic mechanical sounds

    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
    铀
    0.47
    ilerinin
    0.46
    这两个
    0.45
     zaji
    0.45
     oluş
    0.44
    이니까
    0.44
    缮
    0.44
     اخرى
    0.44
    ल्याण
    0.43
     scramble
    0.43
    POSITIVE LOGITS
     de
    0.50
     di
    0.50
     book
    0.50
     semicolon
    0.47
     Esa
    0.47
    s
    0.47
     than
    0.46
     ま
    0.46
     Carlson
    0.45
    ヒル
    0.45
    Activations Density 0.000%

    No Known Activations