© 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. 85505
    Prev
    Next
    INDEX
    Explanations

    let me know

    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
    呖
    -1.80
     forment
    -1.68
     diriger
    -1.66
     hygge
    -1.65
     signaler
    -1.65
     bruin
    -1.64
     jule
    -1.59
     להיות
    -1.59
     mentre
    -1.58
    烔
    -1.58
    POSITIVE LOGITS
     if
    2.13
     that
    2.11
     naše
    2.05
     lámpara
    1.76
     you
    1.67
     lámina
    1.56
    」,
    1.55
     regarding
    1.53
     them
    1.52
     although
    1.52
    Activations Density 0.008%

    No Known Activations