© 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. 41-GEMMASCOPE-2-RES-262K
    7. 33927
    Prev
    Next
    INDEX
    Explanations

    code snippets and symbols

    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
    ⑮
    0.41
    <unused321>
    0.41
     pptd
    0.40
    сима
    0.40
    jería
    0.39
    ట్టిన
    0.38
    耂
    0.38
     vendedores
    0.38
    <unused575>
    0.38
     चिट
    0.37
    POSITIVE LOGITS
    움
    0.42
     turning
    0.36
    super
    0.35
    ദ
    0.35
    indexed
    0.35
     GOP
    0.34
    所在
    0.34
    iid
    0.34
    aughter
    0.34
    coords
    0.34
    Activations Density 0.000%

    No Known Activations