© 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. 85357
    Prev
    Next
    INDEX
    Explanations

    macOS and whisky

    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
    ing
    -4.34
    橚
    -3.08
    ة
    -3.05
    replyreport
    -2.95
    鵟
    -2.91
    怱
    -2.88
     leaſt
    -2.84
    珦
    -2.75
    鈇
    -2.72
     delapan
    -2.66
    POSITIVE LOGITS
    e
    3.89
    d
    2.98
    M
    2.66
    l
    2.58
    n
    2.48
    闼
    2.45
    馘
    2.41
    +"\
    2.38
    section
    2.36
    er
    2.31
    Activations Density 0.008%

    No Known Activations