© 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. 15682
    Prev
    Next
    INDEX
    Explanations

    falling and gravity trajectories

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

    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-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
     हितों
    0.51
     contractual
    0.50
     계약
    0.48
    经纪
    0.48
     договору
    0.47
     बदनाम
    0.47
     créditos
    0.47
    ㊙
    0.47
     договора
    0.47
     депутат
    0.47
    POSITIVE LOGITS
     projectile
    0.90
     gravity
    0.89
     سقوط
    0.88
     Gravity
    0.85
     velocity
    0.83
     ballistic
    0.83
    坠
    0.82
     velocities
    0.82
     projectiles
    0.82
     height
    0.79
    Activations Density 0.046%

    No Known Activations