© 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. 59374
    Prev
    Next
    INDEX
    Explanations

    names and acronyms

    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
    with
    -3.03
    烀
    -2.86
    which
    -2.75
    .,
    -2.70
    You
    -2.66
    ,,
    -2.52
    a
    -2.44
    and
    -2.44
    ly
    -2.42
    ro
    -2.41
    POSITIVE LOGITS
    狳
    2.91
    籥
    2.81
     verzi
    2.80
    蕷
    2.75
    
    2.58
    看到
    2.53
    琑
    2.47
    荜
    2.45
     impos
    2.42
    窳
    2.41
    Activations Density 0.052%

    No Known Activations