© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71493
    Prev
    Next
    INDEX
    Explanations

    uncertainty or contrast

    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
     is
    -1.55
    Either
    -1.52
     juſ
    -1.45
     まる
    -1.45
     enten
    -1.41
     manuten
    -1.40
     vernac
    -1.39
     lenta
    -1.39
     agir
    -1.35
     cifra
    -1.34
    POSITIVE LOGITS
     or
    2.34
     now
    1.82
     etc
    1.47
     on
    1.46
    那就
    1.39
     numerosos
    1.38
    手伝
    1.37
     macetas
    1.36
    hasilkan
    1.36
    なども
    1.34
    Activations Density 0.108%

    No Known Activations