© 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. 221257
    Prev
    Next
    INDEX
    Explanations

    evoked phrases

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

    emphasizes code readability, CCO, allocated

    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
    长时间
    0.46
    askin
    0.43
    ”、
    0.42
    au
    0.42
     semiconductors
    0.42
     그룹
    0.41
    ግር
    0.41
    Mexico
    0.41
    ʐ
    0.40
    疾病
    0.40
    POSITIVE LOGITS
     evaded
    0.49
     accruing
    0.48
    ходом
    0.47
    дання
    0.46
     своїх
    0.46
     slipped
    0.46
     hộ
    0.45
     vattati
    0.45
     deflect
    0.45
     Handlung
    0.44
    Activations Density 0.000%

    No Known Activations