© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128038
    Prev
    Next
    INDEX
    Explanations

    Centre, Index, cloudfront, name

    np_acts-logits-general · gemini-2.5-flash-lite

    xticks, rotation, labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    更是
    0.46
     proyectos
    0.46
     Здесь
    0.44
     също
    0.44
    .
    0.43
    Very
    0.42
     таксама
    0.42
     также
    0.42
    ICK
    0.42
    吳
    0.41
    POSITIVE LOGITS
     Centre
    0.49
     centre
    0.49
    jalpha
    0.47
     Index
    0.47
    cloudfront
    0.47
    index
    0.45
    unused
    0.45
    center
    0.45
    name
    0.44
     NGC
    0.43
    Activations Density 0.003%

    No Known Activations