© 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. 78001
    Prev
    Next
    INDEX
    Explanations

    making up stories or facts

    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
     Juarez
    -0.94
     Woj
    -0.87
     richtig
    -0.83
     ControllerBase
    -0.83
     नीचे
    -0.80
    auff
    -0.80
    Mist
    -0.80
     Juárez
    -0.80
     embal
    -0.78
    БА
    -0.78
    POSITIVE LOGITS
     scenarios
    1.53
     scenario
    1.45
     stories
    1.41
     facts
    1.40
     nonexistent
    1.30
     imaginary
    1.27
     story
    1.24
     circumstances
    1.21
    facts
    1.20
     reasons
    1.20
    Activations Density 0.028%

    No Known Activations