© 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. 5288
    Prev
    Next
    INDEX
    Explanations

    hotlines and safety resources

    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
    ぬいぐるみ
    0.39
     ceremonia
    0.38
    მასრულ
    0.36
    }}^{
    0.34
     idios
    0.34
    Ꮧ
    0.34
     cuadrada
    0.34
    endela
    0.34
    愺
    0.34
    asciiPanel
    0.33
    POSITIVE LOGITS
     G
    0.36
     C
    0.35
     Mo
    0.33
     Không
    0.33
     Alley
    0.33
     ...
    0.33
     Th
    0.33
     bl
    0.33
     Ol
    0.32
     Puls
    0.32
    Activations Density 0.052%

    No Known Activations