© 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. 98622
    Prev
    Next
    INDEX
    Explanations

    Harold followed by name

    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
     Če
    -0.91
     Př
    -0.88
    ochond
    -0.85
     演出
    -0.85
    znac
    -0.85
    一八
    -0.84
    没关系
    -0.83
     Констан
    -0.83
    batal
    -0.82
    lapis
    -0.81
    POSITIVE LOGITS
    swick
    0.86
    ية
    0.85
    川
    0.78
    '].'
    0.75
    ہ
    0.75
    ine
    0.74
    extractor
    0.73
    omoto
    0.73
    Bluetooth
    0.71
    </h3>
    0.69
    Activations Density 0.017%

    No Known Activations