© 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. 24837
    Prev
    Next
    INDEX
    Explanations

    line marking

    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
     patrons
    0.41
    コレート
    0.40
     afterDir
    0.40
    頩
    0.39
    ้ย
    0.39
     Moz
    0.39
    ۓ
    0.39
     allergies
    0.38
     Upstairs
    0.38
    賓
    0.38
    POSITIVE LOGITS
     markings
    1.28
     marking
    1.07
     Marking
    0.95
     lines
    0.95
     marks
    0.91
    marking
    0.91
     mark
    0.87
     markers
    0.87
     marker
    0.86
    mark
    0.86
    Activations Density 0.003%

    No Known Activations