© 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. 71473
    Prev
    Next
    INDEX
    Explanations

    in a file or configuration

    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
    actéristi
    -1.75
    趿
    -1.74
     tristes
    -1.71
     alguns
    -1.65
     noen
    -1.64
    在我
    -1.64
    儅
    -1.60
    nail
    -1.55
     пять
    -1.55
     exprim
    -1.52
    POSITIVE LOGITS
     the
    3.02
     your
    2.86
     both
    2.23
     each
    1.94
     you
    1.94
     our
    1.90
     their
    1.82
     every
    1.79
     various
    1.77
     However
    1.77
    Activations Density 0.245%

    No Known Activations