© 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. 13892
    Prev
    Next
    INDEX
    Explanations

    mathematical and code letter K

    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
    e
    -3.69
    al
    -3.52
    </h3>
    -3.31
    for
    -2.94
    ar
    -2.88
    ↵
    -2.73
    v
    -2.70
    </i>
    -2.59
    o
    -2.59
    ↵↵
    -2.56
    POSITIVE LOGITS
    selbe
    2.67
    ፨
    2.53
    siamo
    2.53
    ſſen
    2.45
    詎
    2.44
    毟
    2.36
    莇
    2.36
     PÅ
    2.33
    ౧
    2.31
     contenir
    2.28
    Activations Density 0.018%

    No Known Activations