© 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. 40-GEMMASCOPE-2-RES-262K
    7. 110547
    Prev
    Next
    INDEX
    Explanations

    evolution of LaTeX environments

    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
    >[</
    0.42
    [-]
    0.42
     [$
    0.42
     Fass
    0.39
     execut
    0.38
     द्र
    0.38
     $[-
    0.38
     [][]
    0.38
     پوش
    0.38
     //[
    0.37
    POSITIVE LOGITS
    Piano
    0.41
    piano
    0.40
    location
    0.39
    tab
    0.39
    Crime
    0.38
    Alive
    0.38
    Exactly
    0.38
    crime
    0.38
    panel
    0.37
    self
    0.37
    Activations Density 0.000%

    No Known Activations