© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2574
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and symbols

    np_acts-logits-general · gemini-2.5-flash-lite

    code delimiters and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused2>
    0.33
     sauces
    0.32
    <unused7>
    0.32
    <unused24>
    0.31
    বারিক
    0.31
    uradaki
    0.30
    樯
    0.30
    料金
    0.29
     calorías
    0.29
     freehold
    0.29
    POSITIVE LOGITS
     ${\
    0.66
     \(
    0.63
     $\
    0.60
     φ
    0.59
     <
    0.59
     $
    0.58
     ω
    0.56
     ϕ
    0.56
     Σ
    0.56
     $$
    0.55
    Activations Density 0.173%

    No Known Activations