© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 245645
    Prev
    Next
    INDEX
    Explanations

    fall, scheduled, fair, follow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (<
    0.52
     berarti
    0.48
     (!)
    0.48
     handicapped
    0.48
     literalmente
    0.48
     (.
    0.48
     LESS
    0.47
     (
    0.46
     diesel
    0.45
     handicap
    0.44
    POSITIVE LOGITS
    你应该
    0.56
    firstname
    0.49
    adım
    0.48
    你会
    0.48
    ቀር
    0.47
    ajouter
    0.47
    anjutkan
    0.46
    you
    0.46
     पत्नी
    0.45
     તમારે
    0.45
    Activations Density 0.001%

    No Known Activations