© 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. 22-GEMMASCOPE-RES-131K
    7. 68249
    Prev
    Next
    INDEX
    Explanations

    label definition files

    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_22/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
     for
    -1.95
     from
    -1.87
     on
    -1.84
     at
    -1.80
     not
    -1.76
     by
    -1.73
     their
    -1.73
     using
    -1.70
     has
    -1.70
     most
    -1.68
    POSITIVE LOGITS
    Após
    1.51
     überprüft
    1.44
    Ingredienti
    1.41
     カジュアル
    1.40
    küche
    1.40
    って
    1.39
     Darum
    1.37
     figliu
    1.36
    埝
    1.34
     nimmer
    1.34
    Activations Density 0.000%

    No Known Activations