© 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. 231
    Prev
    Next
    INDEX
    Explanations

    revolution, spectrum, hunt, spiral, war, wave, continuum, cycle

    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
     and
    -1.45
     Therefore
    -1.33
     montañas
    -1.20
     Hence
    -1.20
     a
    -1.15
     např
    -1.14
     Gewalt
    -1.13
    ↵↵↵↵
    -1.12
    ärna
    -1.12
     歳
    -1.11
    POSITIVE LOGITS
     of
    3.30
     menyen
    1.88
     vokal
    1.85
     that
    1.79
     disiplin
    1.78
     kado
    1.77
     fabrik
    1.75
     kompeti
    1.74
     romantis
    1.74
     brune
    1.73
    Activations Density 0.055%

    No Known Activations