© 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. 22-GEMMASCOPE-RES-131K
    7. 33885
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming expressions

    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_22/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
    σης
    -0.98
    tillinger
    -0.96
     the
    -0.95
     Effects
    -0.91
     about
    -0.90
     explicación
    -0.89
     два
    -0.88
     Gläub
    -0.88
     ботинки
    -0.87
    conver
    -0.86
    POSITIVE LOGITS
     electrified
    1.04
     Cognac
    0.83
     instinctive
    0.81
     onor
    0.81
    選手権
    0.79
     tsar
    0.79
     rabbi
    0.79
     doctorate
    0.79
     enchantment
    0.78
     gik
    0.77
    Activations Density 0.002%

    No Known Activations