© 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. 112265
    Prev
    Next
    INDEX
    Explanations

    media shows and programs

    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
     of
    -1.80
    </tr>
    -1.64
    4
    -1.45
     considerazione
    -1.34
    四十
    -1.30
     maneiras
    -1.29
     prestazioni
    -1.24
    に入って
    -1.24
     podendo
    -1.24
     employees
    -1.23
    POSITIVE LOGITS
    Уважаемые
    1.30
    VideoCapture
    1.29
    Eucalyptus
    1.24
    
    1.23
     seront
    1.18
     reis
    1.17
     休闲
    1.16
    狲
    1.16
    LayoutConstraint
    1.16
    angulo
    1.15
    Activations Density 0.061%

    No Known Activations