© 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. 128135
    Prev
    Next
    INDEX
    Explanations

    late-night talk shows

    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
    翆
    -1.41
     другая
    -1.36
     inset
    -1.24
     あと
    -1.23
     löyty
    -1.20
    ”,
    -1.20
     “
    -1.20
    
    -1.19
    galkan
    -1.19
    </strong>
    -1.17
    POSITIVE LOGITS
    许久
    1.72
    TintMode
    1.48
    却是
    1.40
     tuttavia
    1.37
     "-"
    1.32
    купить
    1.29
    ishes
    1.28
     différente
    1.27
     parfaite
    1.26
     reunión
    1.24
    Activations Density 0.015%

    No Known Activations