© 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. 86831
    Prev
    Next
    INDEX
    Explanations

    Van Centre

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

    information requests

    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
    м
    0.53
     can
    0.52
    []{
    0.49
     bao
    0.48
     mai
    0.45
    <tr>
    0.45
    মাই
    0.45
    who
    0.44
    সম্যান
    0.44
    am
    0.43
    POSITIVE LOGITS
    疥
    0.51
     চীৎকার
    0.47
    ラックス
    0.45
    ustes
    0.44
    ):
    0.44
     जप
    0.43
     Taken
    0.43
     Insulation
    0.42
    মনসিংহ
    0.42
     Aéroport
    0.42
    Activations Density 0.001%

    No Known Activations