© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105532
    Prev
    Next
    INDEX
    Explanations

    detecting state or features

    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_10/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
     cuando
    -2.05
     عندما
    -1.76
    $.
    -1.67
     когда
    -1.60
     quando
    -1.46
     pero
    -1.43
     muchos
    -1.41
     Würde
    -1.41
     queste
    -1.41
     más
    -1.39
    POSITIVE LOGITS
     milyen
    1.60
     whether
    1.48
     which
    1.38
     carottes
    1.30
     where
    1.29
     anew
    1.28
     دى
    1.27
     especially
    1.24
    melho
    1.24
     profundamente
    1.23
    Activations Density 0.074%

    No Known Activations