© 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. 136774
    Prev
    Next
    INDEX
    Explanations

    local laws

    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
    ioxid
    0.46
    reur
    0.41
    🇪
    0.40
    lapse
    0.40
    literature
    0.40
    ٹن
    0.40
    romechanical
    0.40
     пі
    0.39
     ریس
    0.39
    <0x00>
    0.39
    POSITIVE LOGITS
     выбирать
    0.43
     deal
    0.42
    選択
    0.42
     Ain
    0.41
     deals
    0.40
     officially
    0.40
     Snapchat
    0.40
     Choose
    0.40
    स्परिक
    0.39
     ль
    0.38
    Activations Density 0.000%

    No Known Activations