© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 110605
    Prev
    Next
    INDEX
    Explanations

    Chevron, Chevrolet, Chevy

    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
    躥
    -2.59
     inauguración
    -2.56
     Its
    -2.55
    
    -2.53
    啬
    -2.38
     Therefore
    -2.27
     Those
    -2.25
     Could
    -2.25
     Perhaps
    -2.25
     Maybe
    -2.19
    POSITIVE LOGITS
     "
    2.59
    </i>
    2.39
     dibujado
    2.28
     帅气
    2.27
    饪
    2.22
     locales
    2.16
     march
    2.11
    訫
    2.06
    ),
    2.06
    }$
    2.03
    Activations Density 0.004%

    No Known Activations