© 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. 10-GEMMASCOPE-RES-131K
    7. 7800
    Prev
    Next
    INDEX
    Explanations

    defining classes or categories

    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
     wers
    -1.67
     decorados
    -1.66
     dátum
    -1.62
     vakantie
    -1.58
     olvidado
    -1.57
     divertidas
    -1.54
     agujeros
    -1.54
     poderosos
    -1.52
     fenómenos
    -1.52
     salonu
    -1.50
    POSITIVE LOGITS
     are
    2.56
    They
    2.34
    This
    2.31
     that
    2.09
    These
    2.05
    The
    2.05
     who
    1.98
     how
    1.93
    0
    1.92
     from
    1.89
    Activations Density 0.002%

    No Known Activations