© 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. 15692
    Prev
    Next
    INDEX
    Explanations

    motion and state

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

    motion and its direction

    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
     independent
    0.46
    맏
    0.45
    हाय
    0.42
     extremes
    0.42
     censure
    0.41
     gobier
    0.41
    अपना
    0.41
    independent
    0.40
    Independent
    0.40
     privileges
    0.40
    POSITIVE LOGITS
     从
    0.51
     от
    0.50
     från
    0.48
    从
    0.47
     চালিয়ে
    0.46
     Suites
    0.46
     начинает
    0.45
     відпо
    0.45
     Восто
    0.45
     начинают
    0.44
    Activations Density 0.001%

    No Known Activations