© 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. 78022
    Prev
    Next
    INDEX
    Explanations

    stations and selections

    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
     Meals
    -0.98
    rant
    -0.95
     burgers
    -0.91
    Meals
    -0.88
     sandwiches
    -0.88
     tacos
    -0.87
     meals
    -0.85
     burger
    -0.84
     workouts
    -0.82
    '}}>
    -0.82
    POSITIVE LOGITS
     stations
    1.26
     selections
    1.10
    selections
    1.04
     station
    1.01
     Stations
    1.00
    stations
    0.94
     unlimited
    0.91
    Selections
    0.90
     Selections
    0.89
     manned
    0.88
    Activations Density 0.004%

    No Known Activations