© 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. 16-GEMMASCOPE-2-RES-16K
    7. 26
    Prev
    Next
    INDEX
    Explanations

    physical actions 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_16_width_16k_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
    ut
    0.66
    ad
    0.65
    of
    0.63
    z
    0.60
    ses
    0.57
    she
    0.56
    j
    0.56
    q
    0.56
    sa
    0.55
    sn
    0.55
    POSITIVE LOGITS
    ↵↵
    0.53
     corresponde
    0.44
     przyję
    0.44
    大
    0.44
    出会
    0.43
     nú
    0.43
     direcciones
    0.42
    ’
    0.42
    ロウ
    0.41
    ↵
    0.41
    Activations Density 4.117%

    No Known Activations