© 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. 14235
    Prev
    Next
    INDEX
    Explanations

    autonomous weapons, vehicles, ruler

    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
    s
    1.53
    t
    1.38
    y
    1.34
    g
    1.28
    ب
    1.17
    d
    1.12
    ch
    1.08
    sp
    1.05
    c
    1.04
    a
    1.02
    POSITIVE LOGITS
    ino
    1.13
    {
    1.08
     was
    1.02
    ↵
    1.00
     you
    0.96
    0.96
    ้
    0.96
     شما
    0.94
     вас
    0.91
    리
    0.91
    Activations Density 0.003%

    No Known Activations