© 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. 8303
    Prev
    Next
    INDEX
    Explanations

    media statements

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

    wireless system born traffic

    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
    Inflater
    0.44
     parturient
    0.43
    akarane
    0.41
    除此之外
    0.39
    `),
    0.39
    `}
    0.39
    ielen
    0.38
    ){
    0.38
     휴
    0.38
    `
    0.38
    POSITIVE LOGITS
     Susan
    0.65
    Susan
    0.60
    statement
    0.54
     میڈیا
    0.53
     statements
    0.53
    Media
    0.52
     statement
    0.52
    Statement
    0.51
     Media
    0.51
     MEDIA
    0.50
    Activations Density 0.000%

    No Known Activations