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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101434
    Prev
    Next
    INDEX
    Explanations

    numbers followed by specific punctuation or words

    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
    }
    -2.55
     visitó
    -2.36
    橚
    -2.34
    after
    -2.33
    㩒
    -2.30
     dipinto
    -2.28
    栁
    -2.27
     participó
    -2.23
     jarring
    -2.23
     trabajó
    -2.22
    POSITIVE LOGITS
     Our
    2.88
    e
    2.77
    B
    2.61
    ol
    2.34
    “
    2.30
    笮
    2.30
    v
    2.28
    ia
    2.27
    '");
    2.22
    m
    2.22
    Activations Density 0.038%

    No Known Activations