© 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. 249989
    Prev
    Next
    INDEX
    Explanations

    Medicare taxes, Canopy Growth, christmas crafts

    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
    Categor
    0.43
    Transit
    0.42
     }^{-
    0.41
    ARS
    0.40
    加热
    0.40
    categorical
    0.40
    Normal
    0.40
     trialComponents
    0.40
    Authenticate
    0.39
    findOrFail
    0.39
    POSITIVE LOGITS
    واد
    0.51
     何
    0.49
     \%
    0.47
    vođa
    0.46
    無視
    0.46
     फैलाने
    0.46
     संधि
    0.45
    ホース
    0.45
    <unused347>
    0.45
    agnar
    0.44
    Activations Density 0.000%

    No Known Activations