© 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. 105015
    Prev
    Next
    INDEX
    Explanations

    figure and diagram labels

    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
    hasa
    -1.50
    huge
    -1.46
    ourced
    -1.43
     такие
    -1.38
    .«
    -1.35
     retour
    -1.34
     établir
    -1.34
     dahil
    -1.31
     другой
    -1.31
     gef
    -1.31
    POSITIVE LOGITS
     and
    2.11
     because
    1.53
     which
    1.53
     amidst
    1.47
     Many
    1.44
     Perhaps
    1.41
     Maybe
    1.41
     Sometimes
    1.41
     Usually
    1.40
     so
    1.39
    Activations Density 0.012%

    No Known Activations