© 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. 60151
    Prev
    Next
    INDEX
    Explanations

    css background properties

    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
    1
    -2.41
    4
    -2.33
    2
    -2.14
    5
    -2.11
    7
    -2.09
    樒
    -1.98
    6
    -1.95
    女孩子
    -1.95
    x
    -1.95
    or
    -1.91
    POSITIVE LOGITS
    ↵
    2.55
    ஂ
    2.13
    屜
    2.13
    刪除
    2.05
     σελ
    2.03
    癩
    2.03
    schuhe
    2.02
    เกง
    2.00
    𝐃
    1.99
    劻
    1.99
    Activations Density 0.004%

    No Known Activations