© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 8261
    Prev
    Next
    INDEX
    Explanations

    anatomy scans

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

    HLSL, connecting health

    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
    ணம்
    0.41
    ਣੀ
    0.41
    itemName
    0.40
    所需的
    0.40
    豔
    0.39
     amazed
    0.38
     रुप
    0.37
    WHM
    0.37
     '#'
    0.37
     widowed
    0.37
    POSITIVE LOGITS
     sticks
    0.48
     softly
    0.45
    sticks
    0.43
     Slow
    0.43
     Sticks
    0.43
    sticker
    0.42
    slow
    0.41
    षि
    0.40
     गर्ल्स
    0.40
     Slowly
    0.39
    Activations Density 0.000%

    No Known Activations