© 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-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 3873
    Prev
    Next
    INDEX
    Explanations

    numbers and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    0.44
    -
    0.42
     elucidation
    0.41
     distinguishers
    0.39
     namani
    0.39
     fasteners
    0.37
     SUP
    0.37
     tesam
    0.37
    /
    0.37
    getCQL
    0.36
    POSITIVE LOGITS
    ق
    0.83
    س
    0.81
    ج
    0.72
    Y
    0.70
     in
    0.61
    V
    0.59
     be
    0.56
    ע
    0.56
     for
    0.56
    ید
    0.56
    Activations Density 0.753%

    No Known Activations