© 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. 34-GEMMASCOPE-RES-131K
    7. 49769
    Prev
    Next
    INDEX
    Explanations

    movement and direction

    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
     going
    -1.05
    ()]
    -0.99
     tormenta
    -0.95
    logrus
    -0.95
    Reflect
    -0.93
     chimie
    -0.92
    🢒
    -0.91
    뮬
    -0.90
    我會
    -0.90
    consistent
    -0.90
    POSITIVE LOGITS
     into
    2.55
     out
    1.87
     toward
    1.81
     across
    1.80
     off
    1.79
     through
    1.72
     from
    1.70
     onto
    1.52
     along
    1.50
     down
    1.49
    Activations Density 0.047%

    No Known Activations