© 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. 100860
    Prev
    Next
    INDEX
    Explanations

    Gab, Randolph, Thornton

    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
     ส์
    -3.09
    鱚
    -2.98
    之后
    -2.91
     protestas
    -2.75
    Ⲉ
    -2.55
    鹛
    -2.55
    bilisi
    -2.53
    靫
    -2.47
    ászló
    -2.47
    j
    -2.45
    POSITIVE LOGITS
    ↵↵
    2.30
    此次
    2.06
     derzeit
    2.06
     oscura
    1.98
     yaklaşık
    1.95
    粲
    1.94
    "
    1.94
     другому
    1.93
    先前
    1.93
    既然
    1.93
    Activations Density 0.013%

    No Known Activations