© 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. 13255
    Prev
    Next
    INDEX
    Explanations

    idiomatic phrases and specific terms

    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
     and
    -2.05
     Despite
    -1.59
    </b>
    -1.58
     Surprisingly
    -1.56
    ”，
    -1.50
     September
    -1.47
    Despite
    -1.46
     作り方
    -1.46
     October
    -1.45
    Beskrivning
    -1.45
    POSITIVE LOGITS
    ︲
    1.88
    清爽
    1.70
     sometime
    1.66
    惆
    1.65
    鏷
    1.63
    .…
    1.62
    鵙
    1.59
     alguns
    1.59
    .!
    1.59
    ౭
    1.55
    Activations Density 0.005%

    No Known Activations