© 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. 61913
    Prev
    Next
    INDEX
    Explanations

    classify markings

    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
    複
    0.41
     procuring
    0.41
    組み立て
    0.40
    斬
    0.39
    奐
    0.39
    اث
    0.39
    歓
    0.39
    ൗ
    0.39
    િ
    0.39
     contender
    0.38
    POSITIVE LOGITS
     annotations
    0.99
     markers
    0.92
     tags
    0.89
     markings
    0.89
     metadata
    0.87
    markers
    0.84
     Annot
    0.82
     annotate
    0.82
     Markers
    0.82
     annotation
    0.81
    Activations Density 0.002%

    No Known Activations