© 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. 84006
    Prev
    Next
    INDEX
    Explanations

    rights reserved

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

    but light doesn't work that way

    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
    '\
    0.53
    alyse
    0.51
    '$\
    0.49
    $\
    0.49
     NEGLIGENCE
    0.48
    手が
    0.48
     आकलन
    0.47
     оценки
    0.47
    Quer
    0.46
    헉
    0.45
    POSITIVE LOGITS
     designated
    0.45
    ía
    0.44
    άζ
    0.42
     вниз
    0.42
     faced
    0.41
     mediante
    0.41
    itemId
    0.40
    enni
    0.40
    άν
    0.40
     vía
    0.40
    Activations Density 0.000%

    No Known Activations