© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130289
    Prev
    Next
    INDEX
    Explanations

    slow motion

    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_22/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
     уско
    -1.06
     efferves
    -0.89
    laient
    -0.87
    άσ
    -0.84
    ースター
    -0.83
    短い
    -0.83
     hastened
    -0.82
    ènements
    -0.82
     russian
    -0.82
    ekwondo
    -0.82
    POSITIVE LOGITS
     slow
    2.33
     Slow
    2.09
    Slow
    2.05
    slow
    2.05
     slower
    1.92
     slowed
    1.82
     slowest
    1.72
     slows
    1.70
     SLOW
    1.59
    慢
    1.57
    Activations Density 0.182%

    No Known Activations