© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 169114
    Prev
    Next
    INDEX
    Explanations

    research and manga

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    竻
    0.43
    ারিত
    0.41
    @"
    0.41
     gefallen
    0.41
    ীব্র
    0.40
    ந்தை
    0.40
    ాప
    0.40
    henyl
    0.39
    hten
    0.39
    捛
    0.39
    POSITIVE LOGITS
     z
    0.44
    quantum
    0.41
     knowledge
    0.40
     -
    0.39
     ز
    0.38
     rischio
    0.38
     quantum
    0.37
     connaissance
    0.37
     impresa
    0.37
     st
    0.37
    Activations Density 0.000%

    No Known Activations