© 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. 195577
    Prev
    Next
    INDEX
    Explanations

    entity followed by qualifier

    np_acts-logits-general · gemini-2.5-flash-lite

    processing, recognition, interaction, fiction

    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
    꿀
    0.54
    ਲ
    0.49
     threaten
    0.45
     exig
    0.44
    眠
    0.44
    Cancer
    0.42
     احتجاج
    0.42
    threat
    0.42
    斥
    0.42
    rapati
    0.41
    POSITIVE LOGITS
     self
    0.52
     maß
    0.48
     verific
    0.46
     elle
    0.46
    ți
    0.46
    ovaní
    0.44
     पढ़िए
    0.43
     само
    0.43
    assa
    0.43
     ('
    0.43
    Activations Density 0.000%

    No Known Activations