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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 632
    Prev
    Next
    INDEX
    Explanations

    json, url, db, file

    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
    mohon
    -1.84
    carros
    -1.83
     “
    -1.75
    !
    -1.64
    näm
    -1.60
     относительно
    -1.55
     angen
    -1.52
     höl
    -1.51
     verschiedener
    -1.49
    ֢
    -1.49
    POSITIVE LOGITS
    駅前
    1.77
     для
    1.76
     by
    1.73
    3
    1.70
     reinforce
    1.68
     диски
    1.68
    小姐
    1.67
     tüm
    1.67
    rpura
    1.67
    {~
    1.66
    Activations Density 0.074%

    No Known Activations