© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18289
    Prev
    Next
    INDEX
    Explanations

    contrast and exceptions

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

    contrast or exceptions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    および
    0.48
    ！！！！
    0.47
    heard
    0.45
    善良
    0.44
    STEM
    0.42
    鿓
    0.42
    事実
    0.42
    !!!!!!!!
    0.41
    flavor
    0.41
    ଃ
    0.41
    POSITIVE LOGITS
     But
    0.54
     mutta
    0.52
    いますが
    0.52
     אבל
    0.51
     lakini
    0.48
     لكن
    0.48
     difer
    0.48
     maar
    0.48
     sono
    0.47
     rendez
    0.47
    Activations Density 0.000%

    No Known Activations