© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84956
    Prev
    Next
    INDEX
    Explanations

    an addition to something

    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
    ultuous
    -1.95
     Перейти
    -1.92
     tenían
    -1.66
     distintas
    -1.64
    ：……
    -1.63
     siguen
    -1.59
     Ähn
    -1.55
    ๒
    -1.55
    velg
    -1.55
    在住
    -1.54
    POSITIVE LOGITS
    5
    1.97
    v
    1.80
    g
    1.55
    哙
    1.52
     Jahre
    1.51
    🢒
    1.47
    而后
    1.46
    。『
    1.45
     sebagai
    1.45
    却又
    1.45
    Activations Density 0.012%

    No Known Activations