© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 8302
    Prev
    Next
    INDEX
    Explanations

    command or action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    -"
    1.98
    рода
    1.98
    尺度
    1.97
    ‌ها
    1.86
     "
    1.85
    再來
    1.85
    日期
    1.83
     stylistic
    1.80
    、「
    1.80
    лож
    1.80
    POSITIVE LOGITS
    icc
    1.16
     INIT
    1.11
    reter
    1.09
     빠르게
    1.02
    resc
    0.99
     Heal
    0.97
     Wolver
    0.96
    맡
    0.95
    ilis
    0.93
     CONN
    0.92
    Activations Density 0.000%

    No Known Activations