© 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. 1415
    Prev
    Next
    INDEX
    Explanations

    rates per unit

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

    per unit rate

    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
     adipisicing
    0.36
    पटा
    0.36
     Periodic
    0.36
    觑
    0.36
     राक्षस
    0.35
    蠡
    0.35
    ونا
    0.34
     멋
    0.34
     నిర్
    0.34
     राक्ष
    0.33
    POSITIVE LOGITS
     per
    3.95
    per
    2.80
     प्रति
    2.36
     Per
    2.34
    Per
    2.22
     PER
    1.95
    PerHour
    1.63
    PerPage
    1.63
    PER
    1.59
    PerRow
    1.54
    Activations Density 0.361%

    No Known Activations