© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86479
    Prev
    Next
    INDEX
    Explanations

    confirmation input 'y'

    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
    葡萄酒
    -1.79
    észetes
    -1.75
    in
    -1.60
    
    -1.60
    émoc
    -1.55
    am
    -1.45
    ர்
    -1.44
    ap
    -1.42
    }$.
    -1.41
     listopada
    -1.40
    POSITIVE LOGITS
    叱
    1.64
    </h3>
    1.40
     comodidad
    1.38
    ‛
    1.38
     花纹
    1.36
     bandes
    1.36
    様が
    1.35
    桖
    1.35
    !="")
    1.35
    ⬈
    1.34
    Activations Density 0.065%

    No Known Activations