© 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. 113638
    Prev
    Next
    INDEX
    Explanations

    elected or appointed to positions

    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
     onPostExecute
    -2.17
     onCreateView
    -2.00
    titial
    -1.96
     it
    -1.89
     that
    -1.84
     then
    -1.84
    cising
    -1.82
     you
    -1.79
     spécial
    -1.74
     doInBackground
    -1.72
    POSITIVE LOGITS
     the
    1.84
     sirup
    1.67
     Fazit
    1.67
     semblait
    1.65
     laim
    1.61
    了一個
    1.59
     enjeux
    1.56
    </b>
    1.56
     nori
    1.54
     linguaggio
    1.52
    Activations Density 0.029%

    No Known Activations