© 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. 241135
    Prev
    Next
    INDEX
    Explanations

    from the

    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
    日本製
    0.53
    ку
    0.53
    口碑
    0.51
    posal
    0.50
    Ku
    0.50
    number
    0.48
    ク
    0.48
    単
    0.48
    Figure
    0.47
    高质量
    0.46
    POSITIVE LOGITS
     cruel
    0.51
     rapeseed
    0.46
     Pattaya
    0.46
     farklı
    0.44
     oficial
    0.44
     horrible
    0.44
     Riviera
    0.44
     Lua
    0.44
     declarar
    0.43
     gioc
    0.42
    Activations Density 0.000%

    No Known Activations