© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84636
    Prev
    Next
    INDEX
    Explanations

    special characters programming math

    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_34/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
    ímp
    -0.90
    ǚ
    -0.86
    Mening
    -0.85
     conclusione
    -0.82
     informacija
    -0.81
     koš
    -0.81
    garve
    -0.81
    intem
    -0.80
    ┰
    -0.79
    flores
    -0.78
    POSITIVE LOGITS
    .,
    0.93
    _->
    0.91
    _,
    0.86
    $,
    0.85
     *,
    0.80
    [:]
    0.80
    !,
    0.79
     brevet
    0.77
     loup
    0.77
    .:
    0.75
    Activations Density 0.092%

    No Known Activations