© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 14495
    Prev
    Next
    INDEX
    Explanations

    city football clubs

    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
    様です
    -1.43
     dinosaurios
    -1.38
     religiosas
    -1.35
    itarias
    -1.32
     zaraz
    -1.32
     giebt
    -1.30
     maravilla
    -1.28
     adicionales
    -1.28
    žete
    -1.27
     najm
    -1.27
    POSITIVE LOGITS
     of
    1.98
     The
    1.56
     to
    1.39
     only
    1.38
    </b>
    1.38
    craper
    1.33
     только
    1.27
     but
    1.26
    ');
    1.22
    </
    1.20
    Activations Density 0.069%

    No Known Activations