© 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. 84925
    Prev
    Next
    INDEX
    Explanations

    texts about home

    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
     būs
    -1.53
     by
    -1.52
    "…
    -1.45
     pendapatan
    -1.44
     the
    -1.38
    >>>>>
    -1.34
     sebagainya
    -1.34
    eeeee
    -1.34
     женщи
    -1.34
    тка
    -1.30
    POSITIVE LOGITS
    También
    1.64
    買う
    1.51
    endpush
    1.48
    colates
    1.42
     '../../../
    1.41
    什么呢
    1.41
     ціка
    1.41
    ();
    1.40
    出一个
    1.40
    determined
    1.39
    Activations Density 0.007%

    No Known Activations