© 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. 9204
    Prev
    Next
    INDEX
    Explanations

    current + time/state/information

    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
    ي
    1.67
    ও
    1.56
    ك
    1.36
    י
    1.36
    も
    1.35
    在
    1.31
    도
    1.31
    لي
    1.27
    ка
    1.24
    ють
    1.15
    POSITIVE LOGITS
    on
    1.73
    t
    1.49
    st
    1.41
    p
    1.37
    is
    1.35
    h
    1.34
    m
    1.34
    en
    1.28
    u
    1.27
    y
    1.23
    Activations Density 0.059%

    No Known Activations