© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69126
    Prev
    Next
    INDEX
    Explanations

    end of code statement

    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
     to
    -2.30
    at
    -2.16
    H
    -2.08
    os
    -1.96
    but
    -1.91
    as
    -1.84
    S
    -1.80
     F
    -1.79
    v
    -1.79
     each
    -1.77
    POSITIVE LOGITS
    <bos>
    2.20
    嫪
    1.87
     bloques
    1.87
     cukru
    1.80
    geordnete
    1.79
    boyfriend
    1.73
    Bjs
    1.68
     árboles
    1.66
    ?»
    1.62
    kontroll
    1.62
    Activations Density 0.044%

    No Known Activations