© 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. 127256
    Prev
    Next
    INDEX
    Explanations

    loops starting with 1

    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
    糴
    -1.48
    ﮩ
    -1.47
    ܆
    -1.44
    ﮦ
    -1.44
     largely
    -1.44
     produrre
    -1.41
     incrível
    -1.38
    〬
    -1.37
    celotti
    -1.36
     a
    -1.35
    POSITIVE LOGITS
    大約
    1.59
    ;
    1.58
     it
    1.54
     用意
    1.45
    مك
    1.42
     of
    1.39
    3
    1.39
    7
    1.36
     dará
    1.32
    𖥧
    1.30
    Activations Density 0.009%

    No Known Activations