© 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. 13898
    Prev
    Next
    INDEX
    Explanations

    numbers and lists

    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
     ktoré
    -1.58
     that
    -1.56
    hike
    -1.48
     (
    -1.42
     Möglich
    -1.41
     of
    -1.39
     görmek
    -1.36
     мамы
    -1.36
     if
    -1.35
    alimentos
    -1.30
    POSITIVE LOGITS
     “
    1.66
    ുന്നു
    1.57
    ?')
    1.44
     июля
    1.42
     июня
    1.39
    ><><
    1.38
    冶
    1.36
    ”
    1.35
     a
    1.32
     خودش
    1.32
    Activations Density 0.036%

    No Known Activations