© 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. 20726
    Prev
    Next
    INDEX
    Explanations

    conjunctions and descriptors

    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
     then
    0.38
     throughout
    0.35
     levels
    0.35
     repatriation
    0.33
     beyond
    0.33
     deployments
    0.33
    ↵
    0.32
     passages
    0.32
     venues
    0.32
     benchmarks
    0.32
    POSITIVE LOGITS
    และ
    0.59
     અને
    0.55
     आणि
    0.54
     మరియు
    0.53
     و
    0.52
     மற்றும்
    0.52
     ಮತ್ತು
    0.51
     и
    0.50
     और
    0.49
     ਅਤੇ
    0.49
    Activations Density 0.064%

    No Known Activations