© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86448
    Prev
    Next
    INDEX
    Explanations

    extreme or unusual descriptions

    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
    ిన
    -1.49
     perdidos
    -1.38
     kunder
    -1.34
     răm
    -1.32
    mmmm
    -1.32
    ⠶
    -1.28
     sentada
    -1.27
    när
    -1.27
    (*^^
    -1.27
     软
    -1.27
    POSITIVE LOGITS
     amounts
    2.03
     amount
    1.65
     levels
    1.63
    $,
    1.46
    GORITH
    1.45
     Vorgang
    1.45
     for
    1.43
     pubblico
    1.34
     i
    1.32
    瘓
    1.32
    Activations Density 0.039%

    No Known Activations