© 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. 40-GEMMASCOPE-2-RES-262K
    7. 28606
    Prev
    Next
    INDEX
    Explanations

    finding discovery detection

    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_40_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
     맞춰
    0.40
    Animated
    0.40
     대신
    0.39
    เพื่อให้
    0.39
     Purchased
    0.39
     Nearest
    0.38
    ච
    0.38
     ሁሉ
    0.37
     fetched
    0.36
    に合わせて
    0.36
    POSITIVE LOGITS
     lurking
    0.64
     buried
    0.62
     amidst
    0.54
     através
    0.53
     serendip
    0.52
    buried
    0.52
     ходе
    0.51
     through
    0.50
     during
    0.49
     hidden
    0.49
    Activations Density 0.009%

    No Known Activations