© 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. 111562
    Prev
    Next
    INDEX
    Explanations

    confession

    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
     be
    -2.61
    ⩕
    -2.52
    this
    -2.34
     he
    -2.34
    v
    -2.30
    神
    -2.23
    -2.20
     assume
    -2.19
    튿
    -2.16
     incredibly
    -2.14
    POSITIVE LOGITS
    ↵
    2.64
    ⦊
    2.58
    .“
    2.23
    ’
    2.20
    :“
    2.20
     Although
    2.20
    Since
    2.17
    鲮
    2.14
     Since
    2.13
    Because
    2.13
    Activations Density 0.003%

    No Known Activations