© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 11613
    Prev
    Next
    INDEX
    Explanations

    programming languages and scripts

    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_65k_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
     junk
    0.38
    洱
    0.38
     deciso
    0.37
     decisão
    0.36
     rational
    0.36
     Friedman
    0.36
     impl
    0.36
    anneled
    0.36
     significativo
    0.35
     Ziele
    0.35
    POSITIVE LOGITS
    Equivalent
    0.43
    ريبة
    0.41
     મા
    0.40
    더라고
    0.39
    Capability
    0.38
    哦
    0.38
    Migrations
    0.38
    Configurations
    0.38
     러
    0.38
    续
    0.38
    Activations Density 0.001%

    No Known Activations