© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81527
    Prev
    Next
    INDEX
    Explanations

    directional movement input

    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
    tagem
    -0.84
    Francisco
    -0.83
    hängen
    -0.82
    بند
    -0.78
     programación
    -0.77
     Lumen
    -0.76
     ら
    -0.75
     SCHED
    -0.75
     gril
    -0.75
    اعت
    -0.74
    POSITIVE LOGITS
     movement
    1.49
    movement
    1.28
     move
    1.24
     speed
    1.22
     Movement
    1.20
    Movement
    1.16
     walk
    1.12
     Move
    1.09
     forward
    1.08
     Walk
    1.08
    Activations Density 0.009%

    No Known Activations