© 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. 10046
    Prev
    Next
    INDEX
    Explanations

    Czech, Slovak, and other Slavic 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
    鏖
    -2.38
     ailing
    -2.36
     äußerst
    -2.25
     meagre
    -2.22
     Before
    -2.20
    鸯
    -2.20
     has
    -2.17
     flurry
    -2.14
    褔
    -2.13
     arduous
    -2.09
    POSITIVE LOGITS
     saranno
    2.45
    м
    2.39
     algumas
    2.31
    č
    2.31
    簓
    2.30
    š
    2.30
     {
    2.30
     whereby
    2.27
    皷
    2.25
    ing
    2.17
    Activations Density 0.007%

    No Known Activations