© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 22632
    Prev
    Next
    INDEX
    Explanations

    progressing through stages

    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
    ostatic
    0.42
     BatchNorm
    0.42
    $/../../../../
    0.42
    =/
    0.41
     /$
    0.41
     /
    0.40
    bin
    0.37
    abulous
    0.37
     schematic
    0.36
     территориа
    0.36
    POSITIVE LOGITS
     tương
    0.42
     وعد
    0.39
    SourceRequest
    0.38
     beneficio
    0.37
    搶
    0.37
    chromo
    0.37
     жизни
    0.37
     المتوسط
    0.36
     मेघा
    0.36
     diario
    0.36
    Activations Density 0.000%

    No Known Activations