© 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. 24388
    Prev
    Next
    INDEX
    Explanations

    complex risk

    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
     convirt
    0.46
    stas
    0.44
    ROI
    0.44
     Channel
    0.43
    in
    0.42
    JDK
    0.42
    ন
    0.41
     Stake
    0.41
    effort
    0.41
     Selection
    0.41
    POSITIVE LOGITS
    '}$
    0.49
    പരി
    0.46
    कानेर
    0.44
    σει
    0.44
    هُ
    0.42
    ptious
    0.42
     인해
    0.42
    המ
    0.42
    DUCTION
    0.42
     규
    0.42
    Activations Density 0.001%

    No Known Activations