© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77219
    Prev
    Next
    INDEX
    Explanations

    collision, impact, obstruction

    np_acts-logits-general · gemini-2.5-flash-lite

    collision with physical objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invités
    0.41
     使っ
    0.41
    ческую
    0.41
    ோருக்கு
    0.40
    破坏
    0.40
     able
    0.40
    靝
    0.40
     DAMAGE
    0.39
     ቲ
    0.39
     phá
    0.39
    POSITIVE LOGITS
     obstacles
    0.75
     obstáculos
    0.68
    obstacles
    0.63
     obstacle
    0.62
    obstacle
    0.60
     obstructions
    0.60
    Obst
    0.59
     препят
    0.55
     hurdles
    0.53
    障碍
    0.52
    Activations Density 0.088%

    No Known Activations