© 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. 129605
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
     bouteilles
    -1.67
    iyle
    -1.60
     pouvaient
    -1.48
    ఙ
    -1.47
     dezelve
    -1.46
    湮
    -1.45
     alſo
    -1.45
    臃
    -1.44
    Ā
    -1.44
    OLAR
    -1.44
    POSITIVE LOGITS
     its
    1.98
     other
    1.81
     to
    1.70
     still
    1.68
     now
    1.64
     comparatively
    1.53
     two
    1.52
    Kemudian
    1.52
     more
    1.49
     can
    1.45
    Activations Density 0.152%

    No Known Activations