© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101202
    Prev
    Next
    INDEX
    Explanations

    median age

    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
     tanques
    -1.67
     experimentado
    -1.58
     hornear
    -1.57
     and
    -1.53
     but
    -1.52
     which
    -1.52
     alojamientos
    -1.51
    iddhar
    -1.45
     huellas
    -1.45
     jardines
    -1.43
    POSITIVE LOGITS
     of
    2.23
    '
    1.63
     javier
    1.55
     rente
    1.53
     rodrigo
    1.53
    "
    1.52
    man
    1.51
     fendi
    1.50
     felipe
    1.49
    ne
    1.48
    Activations Density 0.028%

    No Known Activations