© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3340
    Prev
    Next
    INDEX
    Explanations

    scoring marks

    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_34/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
     Hornet
    -0.80
     Hilde
    -0.75
    ghal
    -0.74
    нить
    -0.72
    зум
    -0.71
     Phương
    -0.70
    sior
    -0.69
    ➝
    -0.68
    先后
    -0.68
    XF
    -0.66
    POSITIVE LOGITS
     marks
    5.66
     mark
    4.78
    marks
    4.22
     marking
    4.16
    Marks
    4.13
     Marks
    4.09
    mark
    3.64
     MARKS
    3.59
    Marking
    3.38
     Marking
    3.25
    Activations Density 0.043%

    No Known Activations