© 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. 226656
    Prev
    Next
    INDEX
    Explanations

    changing things or stopping

    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
    wissenschaft
    0.55
    ഴിഞ്ഞ
    0.53
    shirts
    0.53
    zeigen
    0.52
    !`
    0.52
    wes
    0.52
    merksamkeit
    0.52
    wikk
    0.51
    ت
    0.51
    kins
    0.51
    POSITIVE LOGITS
    หยุด
    0.44
     Buff
    0.42
     Flam
    0.42
     Stops
    0.41
    构
    0.40
    ↵↵
    0.40
    荷
    0.40
     Flex
    0.39
     Vela
    0.39
     Sutherland
    0.39
    Activations Density 0.000%

    No Known Activations