© 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. 4780
    Prev
    Next
    INDEX
    Explanations

    reading video

    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
    лефон
    0.46
    蛉
    0.46
     enam
    0.45
    LinkForm
    0.45
     storied
    0.42
     Lane
    0.42
    LinkLabel
    0.42
     relazione
    0.42
     kaun
    0.41
     Espanha
    0.41
    POSITIVE LOGITS
    }{
    0.55
     أو
    0.50
    ou
    0.50
     بدء
    0.48
    that
    0.48
     إن
    0.46
    ources
    0.45
    大
    0.45
     removals
    0.44
    concept
    0.43
    Activations Density 0.002%

    No Known Activations