© 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. 39019
    Prev
    Next
    INDEX
    Explanations

    creation or initialization failures

    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
     joyous
    -1.85
     revamped
    -1.84
     spearheaded
    -1.74
     picturesque
    -1.70
     magnificent
    -1.64
     fabulous
    -1.63
     facilita
    -1.63
     consistente
    -1.62
     hugely
    -1.61
    ほんと
    -1.61
    POSITIVE LOGITS
     if
    2.19
     Those
    1.58
     any
    1.54
    .
    1.50
    Some
    1.48
     Some
    1.48
     Often
    1.47
     Surprisingly
    1.46
     Even
    1.45
     your
    1.44
    Activations Density 0.055%

    No Known Activations