© 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. 7155
    Prev
    Next
    INDEX
    Explanations

    step by step

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

    line by line, step by step

    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
    갓
    0.37
    的中
    0.37
    कारक
    0.36
    quirrel
    0.35
     असल्याने
    0.35
     असल्याची
    0.34
    峪
    0.34
    φυ
    0.33
    ksom
    0.33
    Julie
    0.33
    POSITIVE LOGITS
     by
    1.74
    by
    1.57
     By
    1.42
    By
    1.38
    bym
    1.27
     BY
    1.16
     бы
    1.13
    bys
    1.13
    byId
    1.09
    ByName
    1.07
    Activations Density 0.061%

    No Known Activations