© 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. 3284
    Prev
    Next
    INDEX
    Explanations

    regulation and control

    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
     is
    1.34
    ä
    1.15
    ק
    1.01
    大
    0.96
     ומ
    0.95
    ിയുടെ
    0.93
    NE
    0.90
    し
    0.89
     concatenate
    0.86
     {
    0.85
    POSITIVE LOGITS
    on
    1.57
    al
    1.41
    et
    1.23
    el
    1.19
    us
    1.19
    all
    1.11
    ак
    1.08
    oC
    1.02
    re
    1.02
    ু
    1.00
    Activations Density 0.077%

    No Known Activations