© 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. 97383
    Prev
    Next
    INDEX
    Explanations

    charging, falling, vehicle, them

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

    wrist rotations and movements

    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
    dü
    0.57
    ד
    0.56
    ៤
    0.54
    י
    0.49
    ק
    0.48
    tekn
    0.46
    ᐟ
    0.46
    ４
    0.46
    保持
    0.45
    调制
    0.45
    POSITIVE LOGITS
     coworking
    0.55
     word
    0.53
     email
    0.50
     classmates
    0.50
     comparable
    0.50
     emailed
    0.49
     campuses
    0.49
     bureaucr
    0.48
     incompetence
    0.48
     evicted
    0.48
    Activations Density 0.001%

    No Known Activations