© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44867
    Prev
    Next
    INDEX
    Explanations

    highways and motorways

    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
    </h2>
    -2.80
     perdidos
    -2.11
    “,
    -2.09
    weiterlesen
    -1.97
    ”.
    -1.82
    也只能
    -1.80
     الفلسطيني
    -1.78
     consequ
    -1.78
    </em>
    -1.76
    !“
    -1.73
    POSITIVE LOGITS
    we
    2.14
    i
    2.05
    c
    2.03
     Both
    2.02
    m
    1.99
    s
    1.98
    to
    1.95
    阂
    1.89
     Everyone
    1.88
     imagem
    1.88
    Activations Density 0.012%

    No Known Activations