© 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. 69922
    Prev
    Next
    INDEX
    Explanations

    names starting with Jung

    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
     ‘
    -3.05
    jnych
    -2.98
    あります
    -2.92
    there
    -2.77
     remainder
    -2.48
    .’
    -2.48
    我们
    -2.48
    </i>
    -2.34
     undisputed
    -2.27
     They
    -2.25
    POSITIVE LOGITS
    靣
    3.06
    {
    2.94
     싶
    2.69
    est
    2.58
     вижу
    2.58
     позволит
    2.56
     животные
    2.42
    }$
    2.38
     produkcji
    2.31
    which
    2.27
    Activations Density 0.001%

    No Known Activations