© 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. 59530
    Prev
    Next
    INDEX
    Explanations

    Saxon, Saxony, English, myeloid

    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
    .
    -2.59
    鉏
    -2.52
    肏
    -2.47
    鱨
    -2.23
     been
    -2.19
     uſed
    -2.16
     новую
    -2.09
    屨
    -2.05
     referrerpolicy
    -1.99
    doctoral
    -1.98
    POSITIVE LOGITS
    5
    2.67
    2
    2.44
    4
    2.23
    7
    2.20
    9
    2.17
    8
    1.95
    も
    1.90
    3
    1.89
    1
    1.86
    期間限定
    1.85
    Activations Density 0.010%

    No Known Activations