© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8607
    Prev
    Next
    INDEX
    Explanations

    from + topic

    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
     erfordert
    -3.00
     '
    -2.97
    ",
    -2.89
     hoher
    -2.89
     verbess
    -2.80
    ]
    -2.80
         
    -2.77
    this
    -2.73
     "
    -2.69
     dauert
    -2.69
    POSITIVE LOGITS
    ཋ
    3.52
    鹀
    3.03
    鹪
    2.83
    緜
    2.81
    蘩
    2.78
    蹓
    2.78
    鉏
    2.78
    婼
    2.73
    鼯
    2.73
    इटम
    2.64
    Activations Density 0.000%

    No Known Activations