© 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. 101204
    Prev
    Next
    INDEX
    Explanations

    Roberto followed by a 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_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
    艫
    -2.86
     unsere
    -2.75
    你
    -2.61
    
    -2.52
     shabby
    -2.47
     aching
    -2.45
    傒
    -2.45
    larda
    -2.45
    ⤥
    -2.36
     exorbitant
    -2.34
    POSITIVE LOGITS
    甞
    3.30
    薆
    3.30
    埽
    3.08
    饪
    3.08
    ༵
    3.03
    赑
    3.02
    镦
    2.94
    阏
    2.89
    蚡
    2.83
    鼍
    2.75
    Activations Density 0.012%

    No Known Activations