© 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. 85344
    Prev
    Next
    INDEX
    Explanations

    touches, bittersweet emotions, genitalia

    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
     Baillargeon
    -2.52
    鉕
    -2.30
     nahil
    -2.22
     mantener
    -2.17
    豨
    -2.09
    而在
    -2.02
    饜
    -2.02
     freestanding
    -2.02
     distinto
    -1.99
    )$
    -1.97
    POSITIVE LOGITS
    ۔
    2.63
    ،
    2.61
     fingertips
    2.45
     In
    2.44
    鸶
    2.42
    
    2.30
    there
    2.28
    我没有
    2.25
     этого
    2.22
    ‪.‬‬
    2.19
    Activations Density 0.002%

    No Known Activations