© 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. 7158
    Prev
    Next
    INDEX
    Explanations

    definitions with colons and asterisks

    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
    들도
    0.43
     Analyses
    0.42
     दिसून
    0.42
    事实
    0.41
     significative
    0.41
    ல்க
    0.41
    逊
    0.41
     것도
    0.40
     разнообраз
    0.40
     사실
    0.40
    POSITIVE LOGITS
    explained
    0.41
    stands
    0.41
     initials
    0.41
     daarbij
    0.41
     explained
    0.40
    qquad
    0.38
     glossary
    0.38
     components
    0.38
     acronym
    0.38
     stands
    0.37
    Activations Density 0.145%

    No Known Activations