© 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. 43245
    Prev
    Next
    INDEX
    Explanations

    capabilities

    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
    釭
    -2.73
    鬭
    -2.72
    ⵈ
    -2.63
    🍺
    -2.59
    鹛
    -2.55
    ！"
    -2.55
    蕷
    -2.44
    蠖
    -2.41
    鏐
    -2.39
    覬
    -2.36
    POSITIVE LOGITS
    <em>
    2.80
     “
    2.80
    U
    2.58
    6
    2.55
    (“
    2.48
    In
    2.44
    0
    2.41
    ”،
    2.39
    стреча
    2.39
    4
    2.38
    Activations Density 0.002%

    No Known Activations