© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117099
    Prev
    Next
    INDEX
    Explanations

    movement and stillness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tiéndose
    -0.85
    wellen
    -0.73
    nischer
    -0.71
    Fernsehserie
    -0.70
    OTING
    -0.68
     リア
    -0.68
     vissza
    -0.67
    ཞ
    -0.67
    tande
    -0.67
    筲
    -0.65
    POSITIVE LOGITS
     movement
    5.28
     moving
    5.25
     move
    5.22
    move
    4.44
     moved
    4.38
     moves
    4.25
    Moving
    4.22
    Move
    4.13
    moving
    4.09
    movement
    4.00
    Activations Density 0.267%

    No Known Activations