© 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. 45229
    Prev
    Next
    INDEX
    Explanations

    numbers containing 3

    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
    ん
    -2.28
     Then
    -2.22
    
    -2.19
     Also
    -2.16
     επίσης
    -2.11
    )
    -2.09
    тися
    -2.02
     también
    -1.97
    場面
    -1.92
     disregarding
    -1.91
    POSITIVE LOGITS
    谂
    2.64
    3
    2.48
     is
    2.38
    玧
    2.33
    鲣
    2.31
    ">
    2.17
    ”)
    2.16
    )"
    2.16
    ”。
    2.14
     ибо
    2.11
    Activations Density 0.275%

    No Known Activations