© 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. 12014
    Prev
    Next
    INDEX
    Explanations

    verbs of motion and conversation

    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
     Stopping
    -1.13
     Stopped
    -1.06
    Stopping
    -1.00
     Stops
    -0.98
    STOP
    -0.98
    gherita
    -0.93
    arrivée
    -0.92
     STOP
    -0.88
     Stop
    -0.87
     Arrival
    -0.87
    POSITIVE LOGITS
     walk
    2.09
     walked
    1.98
     walking
    1.98
     leaving
    1.92
     leave
    1.84
     walks
    1.74
    walk
    1.71
     departure
    1.63
     depart
    1.62
     exit
    1.59
    Activations Density 0.010%

    No Known Activations