© 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. 128034
    Prev
    Next
    INDEX
    Explanations

    .NET Web API controller

    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
    ’
    -2.39
    媖
    -1.76
     are
    -1.73
    }$
    -1.65
    ！”
    -1.60
     signora
    -1.54
    "]="
    -1.54
    是
    -1.48
     figlia
    -1.48
     nuova
    -1.48
    POSITIVE LOGITS
     "
    1.63
    нення
    1.57
    ."
    1.57
    tifies
    1.51
    #"
    1.50
     見え
    1.50
     אך
    1.49
    マジ
    1.48
     temor
    1.48
    ほんとに
    1.41
    Activations Density 0.013%

    No Known Activations