© 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. 193091
    Prev
    Next
    INDEX
    Explanations

    goal or need

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

    limited concepts, hardware-centric, generate

    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
     soooo
    0.51
     sooo
    0.48
     ticked
    0.47
     NADH
    0.45
    使用者
    0.44
     BC
    0.43
     Wolff
    0.42
     offender
    0.42
    
    0.42
     тако
    0.41
    POSITIVE LOGITS
    *}\
    0.57
    ıları
    0.53
    Net
    0.50
    ạc
    0.49
    aleza
    0.49
    ancienne
    0.49
    avez
    0.48
    posals
    0.48
    vez
    0.48
    Az
    0.48
    Activations Density 0.000%

    No Known Activations