© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74544
    Prev
    Next
    INDEX
    Explanations

    jihad and ji

    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
     撮っ
    -3.16
    骈
    -3.05
     That
    -3.00
    籀
    -2.77
    
    -2.67
    仃
    -2.66
    瀦
    -2.61
     niž
    -2.52
    後記
    -2.47
    𖤣
    -2.47
    POSITIVE LOGITS
    s
    3.98
    "
    3.58
    ’
    3.36
    '
    3.20
    2
    3.17
    3
    3.08
    All
    3.05
    P
    3.03
    v
    2.91
    ва
    2.84
    Activations Density 0.003%

    No Known Activations