© 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. 7575
    Prev
    Next
    INDEX
    Explanations

    ranges or scores

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

    entity-relationshipProduct-Producer

    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
     ـ
    0.48
     －
    0.47
    ／
    0.35
    ,-\
    0.34
    －－
    0.34
    复杂度
    0.33
    脿
    0.33
     –,
    0.33
    ﹐
    0.33
     ―
    0.33
    POSITIVE LOGITS
    
    0.41
     ]]
    0.36
    IFIER
    0.35
     Ấ
    0.35
     ಭಾಗ
    0.35
     المواد
    0.33
     Ако
    0.33
     ఏద
    0.33
    avkhat
    0.33
    breve
    0.32
    Activations Density 0.064%

    No Known Activations