© 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. 1775
    Prev
    Next
    INDEX
    Explanations

    outcomes and data

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

    a harmless AI assistant

    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
    8
    0.64
    <0xB9>
    0.64
    ８
    0.62
     ۸
    0.59
    
    0.57
     எட்டு
    0.55
    ۸
    0.52
    ٨
    0.52
     eight
    0.51
    ၈
    0.50
    POSITIVE LOGITS
    Бы
    0.44
    𝘣
    0.42
    htm
    0.40
    hyun
    0.39
     במ
    0.38
    如有
    0.38
    Fifty
    0.38
    rbind
    0.38
    жор
    0.37
     Бы
    0.37
    Activations Density 0.285%

    No Known Activations