© 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. 75465
    Prev
    Next
    INDEX
    Explanations

    any questions or issues

    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
    like
    -1.98
    of
    -1.80
    as
    -1.80
    -
    -1.73
     a
    -1.73
    while
    -1.65
     facendo
    -1.62
     same
    -1.59
     beliebtesten
    -1.59
    :
    -1.55
    POSITIVE LOGITS
    觧
    1.75
    鵟
    1.73
     klasa
    1.70
     blancas
    1.68
    趼
    1.67
     delikat
    1.66
    nými
    1.65
    ཫ
    1.60
    krok
    1.58
    liputi
    1.57
    Activations Density 0.014%

    No Known Activations