© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 5303
    Prev
    Next
    INDEX
    Explanations

    code delimiters and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    
    1.69
     
    1.56
    .
    1.55
     ■
    1.49
    
    1.45
    ■
    1.36
     ("
    1.34
     "-
    1.33
    
    1.33
     "/
    1.31
    POSITIVE LOGITS
     `
    3.46
    `
    3.16
    `(
    2.43
     `$
    2.38
     (`
    2.33
    `.
    2.29
    `-
    2.24
     `.
    2.20
     [`
    2.16
    (`
    2.15
    Activations Density 1.160%

    No Known Activations