© 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. 59375
    Prev
    Next
    INDEX
    Explanations

    C1 prefix

    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
    
    -2.45
    hogany
    -2.44
    ⽌
    -2.30
    瀦
    -2.27
     ocurrió
    -2.22
     connotation
    -2.20
     successivamente
    -2.19
    BeanFactory
    -2.17
    
    -2.13
     ayudó
    -2.02
    POSITIVE LOGITS
     \
    2.58
    另一
    2.50
    ();
    2.39
    w
    2.36
    \_
    2.25
    i
    2.25
    ’
    2.25
    en
    2.23
    ma
    2.17
     ваши
    2.16
    Activations Density 0.026%

    No Known Activations