© 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. 34-GEMMASCOPE-RES-131K
    7. 6892
    Prev
    Next
    INDEX
    Explanations

    orchestra, quartet, ballet names

    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_34/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
    Neden
    -0.78
    Analyse
    -0.77
    Performances
    -0.73
    過ぎて
    -0.72
     $\$
    -0.71
    modified
    -0.70
    Cringe
    -0.70
    🩱
    -0.69
     vien
    -0.69
    బ
    -0.68
    POSITIVE LOGITS
     lunchtime
    1.06
    yaf
    0.97
     broadcaster
    0.89
     Vordergrund
    0.88
     Quercus
    0.85
    孔
    0.84
     commas
    0.84
     effetto
    0.84
    UBS
    0.82
    Choisissez
    0.82
    Activations Density 0.040%

    No Known Activations