© 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. 71833
    Prev
    Next
    INDEX
    Explanations

    The organization names

    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
     extranjera
    -1.71
    -
    -1.66
     
    -1.59
     essenciais
    -1.41
     femininos
    -1.37
    を利用
    -1.34
    一颗
    -1.34
     tecnológicos
    -1.31
     establecidas
    -1.30
     sanitarios
    -1.30
    POSITIVE LOGITS
     which
    1.80
     that
    1.78
     of
    1.68
     शुर
    1.46
     so
    1.46
     Lokasi
    1.45
     from
    1.44
    rozum
    1.40
     خارجية
    1.36
     piccola
    1.35
    Activations Density 0.083%

    No Known Activations