© 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. 22-GEMMASCOPE-RES-131K
    7. 26951
    Prev
    Next
    INDEX
    Explanations

    usual followed by a noun

    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_22/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
     wondrous
    -2.91
    臜
    -2.86
    跸
    -2.78
     .......
    -2.75
     vijf
    -2.75
    でも
    -2.73
     ludicrous
    -2.69
     -----
    -2.66
    嫑
    -2.66
    OUTUBE
    -2.59
    POSITIVE LOGITS
    a
    3.25
    s
    3.08
     allow
    2.89
     makes
    2.83
    塤
    2.81
     takes
    2.75
     undeniably
    2.72
     meticulously
    2.69
     epitom
    2.61
     give
    2.59
    Activations Density 0.014%

    No Known Activations