© 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. 110535
    Prev
    Next
    INDEX
    Explanations

    articles of use

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

    associated with project completion

    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
     finally
    0.48
     ഡി
    0.47
    コント
    0.46
    淩
    0.46
     autumn
    0.45
     アル
    0.45
     органі
    0.45
    РА
    0.45
     де
    0.45
     Moot
    0.44
    POSITIVE LOGITS
    ៖
    0.53
    uos
    0.51
    igas
    0.46
    ipine
    0.45
    og
    0.44
    वतात
    0.44
    os
    0.44
    responding
    0.43
    atars
    0.43
    ന്‍റെ
    0.43
    Activations Density 0.001%

    No Known Activations