© 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
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 9051
    Prev
    Next
    INDEX
    Explanations

    words/acronyms followed by specific continuations

    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
     be
    1.11
    ।
    0.73
     in
    0.71
    ។
    0.71
     for
    0.70
     as
    0.67
     can
    0.66
     you
    0.66
    Y
    0.63
    L
    0.62
    POSITIVE LOGITS
    ↵↵
    0.69
    os
    0.63
    quele
    0.62
     übrigens
    0.61
    åll
    0.58
    的其他
    0.58
    quela
    0.57
    の部分
    0.56
    on
    0.55
    lar
    0.55
    Activations Density 0.172%

    No Known Activations