© 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. 21233
    Prev
    Next
    INDEX
    Explanations

    Engel, Chopin, bulldog, steer

    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
    ים
    -3.33
    -
    -3.00
    s
    -2.97
    ی
    -2.75
    ’
    -2.75
    We
    -2.67
    荩
    -2.55
    他的
    -2.47
                
    -2.45
     was
    -2.44
    POSITIVE LOGITS
    珢
    3.16
    镚
    2.94
    肫
    2.88
    酲
    2.78
     αλλά
    2.66
     мужская
    2.61
     クラブ
    2.61
    「
    2.59
    ᩠
    2.55
    躝
    2.52
    Activations Density 0.023%

    No Known Activations