© 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. 5053
    Prev
    Next
    INDEX
    Explanations

    email and social media identifiers

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

    code annotations and decorators

    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
     (\"
    0.44
     ({\
    0.44
    "><?=$
    0.42
    
    0.41
    攵
    0.41
    䅧
    0.40
    \"
    0.39
    ◅
    0.39
    趄
    0.39
    ✓
    0.37
    POSITIVE LOGITS
     @
    3.91
    @
    3.73
     @_
    2.81
    (@
    2.80
    .@
    2.77
    \@
    2.70
    ＠
    2.69
    ,@
    2.67
    @(
    2.67
     `@
    2.61
    Activations Density 0.100%

    No Known Activations