© 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. 64374
    Prev
    Next
    INDEX
    Explanations

    boolean values (true, false, 1, 0)

    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
    щать
    -0.82
     colegio
    -0.79
    İ
    -0.79
    verb
    -0.78
     Ultrasound
    -0.75
     stair
    -0.75
    Travel
    -0.75
     kennis
    -0.74
     verb
    -0.72
    ěž
    -0.72
    POSITIVE LOGITS
     truth
    1.66
     false
    1.53
     falsehood
    1.50
     Truth
    1.45
    false
    1.45
     False
    1.41
     boolean
    1.35
     bool
    1.34
     True
    1.33
    truth
    1.32
    Activations Density 0.048%

    No Known Activations