© 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. 101721
    Prev
    Next
    INDEX
    Explanations

    Rue, Jax, Royce

    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
    -2.81
    蛧
    -2.77
    玗
    -2.64
    ſelves
    -2.55
    amoan
    -2.55
    裊
    -2.53
    傒
    -2.53
    抡
    -2.53
    rowable
    -2.47
    韞
    -2.45
    POSITIVE LOGITS
    '
    3.53
    2
    2.73
    ↵
    2.69
     praktische
    2.66
    "
    2.64
     heilig
    2.61
    .
    2.61
     The
    2.61
     ungefähr
    2.48
    ために
    2.31
    Activations Density 0.003%

    No Known Activations