© 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. 9047
    Prev
    Next
    INDEX
    Explanations

    collision detection

    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
    ):
    0.92
    ctions
    0.90
    );
    0.86
    ‌است
    0.86
    ור
    0.83
     in
    0.82
    fluss
    0.82
    ’
    0.82
    ريقة
    0.81
    GA
    0.80
    POSITIVE LOGITS
    ки
    1.32
     collisions
    1.24
    ๑
    1.09
    1
    1.08
     collision
    1.05
     collide
    1.02
    碰撞
    1.01
    ine
    0.98
    ก
    0.96
    6
    0.96
    Activations Density 0.003%

    No Known Activations