© 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. 41-GEMMASCOPE-2-RES-262K
    7. 2097
    Prev
    Next
    INDEX
    Explanations

    stopping bleeding

    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_all/layer_41_width_262k_l0_big
    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
    CurrentImage
    0.46
    ื่อ
    0.44
    ッキリ
    0.43
    یشن
    0.41
    ່ວ
    0.41
    ⸩
    0.40
     álgebra
    0.40
     ইমরান
    0.40
    غو
    0.40
    <unused1049>
    0.40
    POSITIVE LOGITS
     bleeding
    1.56
     bleed
    1.48
    出血
    1.34
     Ble
    1.30
    Ble
    1.27
     bled
    1.27
     ble
    1.23
    bleed
    1.10
    ble
    1.05
    bleeds
    1.05
    Activations Density 0.009%

    No Known Activations