© 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. 10-GEMMASCOPE-RES-131K
    4. 130709
    Prev
    Next
    INDEX
    Explanations

    confident

    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
     exceptionally
    -2.80
     delightfully
    -2.70
     ridiculously
    -2.52
     decidedly
    -2.47
     strikingly
    -2.45
     magnificent
    -2.45
     quintessential
    -2.45
     marvelous
    -2.44
     Quando
    -2.41
     относятся
    -2.38
    POSITIVE LOGITS
    Without
    3.19
    ﹐
    2.75
    Like
    2.70
    Only
    2.64
    Although
    2.61
    Despite
    2.58
    Using
    2.52
    Just
    2.45
    一旁的
    2.45
    Through
    2.44
    Activations Density 0.002%

    No Known Activations