© 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. 1640
    Prev
    Next
    INDEX
    Explanations

    numbers and years

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

    numbers and calculations

    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
    狯
    0.39
     গ্রহণের
    0.37
    ዎት
    0.36
    จัย
    0.36
    餑
    0.35
     psychiat
    0.35
     लिखने
    0.35
    明显的
    0.35
    ల్లు
    0.35
    没人
    0.35
    POSITIVE LOGITS
    s
    0.44
    class
    0.40
    th
    0.39
    nov
    0.38
    m
    0.38
    render
    0.37
    to
    0.37
    gover
    0.37
    a
    0.37
    deleg
    0.36
    Activations Density 0.051%

    No Known Activations