© 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. 21549
    Prev
    Next
    INDEX
    Explanations

    research in context

    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
     their
    -2.30
     your
    -2.13
     the
    -1.98
     they
    -1.98
     some
    -1.89
    -”
    -1.84
     defekt
    -1.83
     December
    -1.81
     our
    -1.73
     what
    -1.71
    POSITIVE LOGITS
    锶
    1.88
     heeft
    1.87
    mored
    1.71
     regardant
    1.70
    全都
    1.70
    学的
    1.69
    údos
    1.62
    大幅
    1.61
    箔
    1.61
     hizo
    1.58
    Activations Density 0.006%

    No Known Activations