© 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. 9426
    Prev
    Next
    INDEX
    Explanations

    text markup characters

    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
    बि
    -1.80
    ruckt
    -1.66
    存知
    -1.55
    atzung
    -1.51
    \
    -1.43
     brevemente
    -1.42
     but
    -1.41
     kteří
    -1.41
    kkue
    -1.34
    intă
    -1.34
    POSITIVE LOGITS
     после
    1.69
     또는
    1.45
    Again
    1.45
    sistence
    1.41
     всех
    1.40
     solicitó
    1.37
     -
    1.36
    1.36
     olması
    1.34
    涧
    1.34
    Activations Density 0.014%

    No Known Activations