© 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. 1914
    Prev
    Next
    INDEX
    Explanations

    common phrases following keywords

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

    Here's how

    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
    <unused2213>
    0.20
    当前的
    0.18
     safest
    0.17
     fastest
    0.17
    াদিত
    0.17
     იქ
    0.17
     equine
    0.17
     നിരവധി
    0.17
    典型的
    0.17
    远处
    0.17
    POSITIVE LOGITS
     ….
    0.19
     Gopal
    0.18
    يئة
    0.18
    う
    0.18
     \...
    0.18
    =\"
    0.18
     it
    0.17
    velop
    0.17
     públicos
    0.17
    ‐
    0.17
    Activations Density 0.413%

    No Known Activations