© 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. 34-GEMMASCOPE-RES-131K
    7. 31449
    Prev
    Next
    INDEX
    Explanations

    women's Ashes

    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_34/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
     utilisateurs
    -0.75
    NELL
    -0.75
    HON
    -0.74
     уте
    -0.73
    の下
    -0.71
    vedades
    -0.71
    afford
    -0.69
    ἵ
    -0.68
    OX
    -0.68
    arctic
    -0.68
    POSITIVE LOGITS
     ash
    4.53
     ashes
    4.22
     Ashes
    3.47
     Ash
    3.42
     ashtray
    3.25
     asht
    3.11
    Ash
    3.11
     ASH
    3.03
    ash
    2.67
    ashes
    2.66
    Activations Density 0.109%

    No Known Activations