© 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. 31-GEMMASCOPE-2-RES-262K
    7. 15682
    Prev
    Next
    INDEX
    Explanations

    gravity and falling objects

    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_31_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
     réunion
    0.48
     contractual
    0.47
    มาชิก
    0.47
     हितों
    0.46
    党委
    0.46
     créditos
    0.46
    勛
    0.46
     депутат
    0.45
     главных
    0.45
    บท
    0.44
    POSITIVE LOGITS
     gravity
    0.90
     velocity
    0.84
     Gravity
    0.83
     projectile
    0.80
     acceleration
    0.79
     velocities
    0.78
     سقوط
    0.78
     falling
    0.77
    坠
    0.77
     height
    0.76
    Activations Density 0.108%

    No Known Activations