© 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. 6931
    Prev
    Next
    INDEX
    Explanations

    arrow keys or pointing

    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
     in
    1.23
    ক
    1.20
    _
    1.20
     at
    1.18
     در
    1.15
    \
    1.03
    ي
    1.03
    {
    0.93
    को
    0.92
     oeuvre
    0.91
    POSITIVE LOGITS
    箭头
    1.25
    Arrow
    1.20
    AY
    1.09
    Arrows
    1.08
    箭
    1.08
     arrows
    1.02
    3
    1.02
     arrow
    1.00
    4
    0.96
    ى
    0.96
    Activations Density 0.006%

    No Known Activations