© 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. 59987
    Prev
    Next
    INDEX
    Explanations

    Russian words like подобный

    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
    </h3>
    -3.45
    </sub>
    -2.88
    瓩
    -2.61
    ziná
    -2.47
     religiously
    -2.45
    塤
    -2.41
    趵
    -2.38
    蛧
    -2.30
    rewsbury
    -2.30
     Reglamento
    -2.23
    POSITIVE LOGITS
    2
    4.13
    3
    3.03
     \
    2.80
    色んな
    2.58
    我也不
    2.52
    薅
    2.50
    ’
    2.50
     $-$
    2.45
     {
    2.44
    很快就
    2.44
    Activations Density 0.001%

    No Known Activations