© 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. 58980
    Prev
    Next
    INDEX
    Explanations

    starts of phrases and code

    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
     Königreich
    -0.80
    났
    -0.76
    textsc
    -0.75
     santuario
    -0.73
    Beschreibung
    -0.72
     furthermore
    -0.71
    dermal
    -0.69
     pleno
    -0.69
     funktionieren
    -0.68
    onomi
    -0.68
    POSITIVE LOGITS
     LIABILITY
    0.88
    棻
    0.84
    匹配
    0.82
    Hierarchy
    0.81
    聞こ
    0.81
    tsun
    0.81
     Liability
    0.78
    Tyler
    0.78
    宮
    0.78
    <mask>
    0.76
    Activations Density 0.002%

    No Known Activations