© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 3624
    Prev
    Next
    INDEX
    Explanations

    real numbers and functions

    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
     enorme
    -1.88
    </b>
    -1.73
     him
    -1.65
    am
    -1.58
     très
    -1.58
     drie
    -1.57
     desesper
    -1.53
     racional
    -1.53
     studi
    -1.52
     conveniente
    -1.51
    POSITIVE LOGITS
     शुर
    1.84
     from
    1.77
     飲
    1.59
     wiederhol
    1.59
    .}(
    1.56
     ausdrück
    1.56
     with
    1.56
    agory
    1.45
     ИН
    1.45
    鷄
    1.44
    Activations Density 0.016%

    No Known Activations