© 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. 198781
    Prev
    Next
    INDEX
    Explanations

    post the first comment

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

    making things

    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
    沒
    0.50
     Hang
    0.43
     Hao
    0.43
     Gibt
    0.43
    我們先
    0.42
    ంది
    0.42
     hao
    0.42
     שא
    0.41
    潾
    0.41
     Miss
    0.41
    POSITIVE LOGITS
    )>=
    0.47
    ローブ
    0.45
     deadlock
    0.45
    سام
    0.45
    inent
    0.44
     eyebrow
    0.44
    continent
    0.43
    ങ്ങള
    0.43
    あっ
    0.42
    ्ला
    0.42
    Activations Density 0.001%

    No Known Activations