© 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. 8518
    Prev
    Next
    INDEX
    Explanations

    questions about action or self

    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
    و
    0.40
    er
    0.39
    io
    0.35
    ри
    0.32
    comme
    0.32
    os
    0.31
    та
    0.31
    1
    0.31
    h
    0.31
    it
    0.30
    POSITIVE LOGITS
     
    0.33
     samego
    0.29
     impromptu
    0.28
     proactively
    0.28
     %``
    0.27
     😂😂
    0.27
     to
    0.27
     demeanor
    0.27
     of
    0.25
     warrantless
    0.25
    Activations Density 3.409%

    No Known Activations