© 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. 39608
    Prev
    Next
    INDEX
    Explanations

    pleural effusion, ggplot plots, direct search

    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
     {
    -3.05
    鱻
    -2.78
    </h3>
    -2.67
     For
    -2.61
    n
    -2.55
     для
    -2.50
    </strong>
    -2.47
     worauf
    -2.45
    I
    -2.44
    ."
    -2.42
    POSITIVE LOGITS
    蹰
    2.83
    ⸫
    2.72
    嚒
    2.64
    iſter
    2.63
    茕
    2.53
     unſ
    2.48
    鴬
    2.45
    谖
    2.41
     mijn
    2.39
    beging
    2.39
    Activations Density 0.008%

    No Known Activations