Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 18379
    Prev
    Next
    INDEX
    Explanations

    EntityFramework Core

    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_40_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
    hmad
    0.44
     Oiseaux
    0.41
     ಕ್ಷೇತ್ರ
    0.39
     %``
    0.38
    GUN
    0.38
     addCriterion
    0.38
     ဘ
    0.38
     కా
    0.37
     Ahmad
    0.37
    Gun
    0.37
    POSITIVE LOGITS
     devices
    0.42
     maladies
    0.41
     indes
    0.39
    性感
    0.39
     possessions
    0.38
     mean
    0.37
     raus
    0.37
     find
    0.37
     aberrations
    0.37
     become
    0.36
    Activations Density 0.000%

    No Known Activations