© 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. 31-GEMMASCOPE-2-RES-262K
    7. 137600
    Prev
    Next
    INDEX
    Explanations

    apps and segmentation

    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_31_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
     مزید
    0.55
    <unused1059>
    0.51
    ligo
    0.50
    മ്പി
    0.50
    കൊണ്ട്
    0.50
    <unused513>
    0.49
    届け
    0.49
     बालकनियां
    0.49
    y
    0.49
    ピー
    0.49
    POSITIVE LOGITS
    I
    0.48
     initiating
    0.46
     a
    0.43
    час
    0.43
     hourglass
    0.43
    د
    0.43
    ्राष्ट्रीय
    0.42
     offense
    0.41
     в
    0.40
     switching
    0.40
    Activations Density 0.000%

    No Known Activations