© 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. 8651
    Prev
    Next
    INDEX
    Explanations

    blind children

    np_acts-logits-general · gemini-2.5-flash-lite

    the literal word “blind” (or its occurrence in terms like “blindness,” “blind spots,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     he
    -2.98
     ”
    -2.86
    蓠
    -2.84
     
    -2.75
     “
    -2.75
     diğer
    -2.73
    缡
    -2.59
     ‘
    -2.58
     أحد
    -2.47
    揽
    -2.44
    POSITIVE LOGITS
    獁
    3.25
    禤
    3.06
    婓
    2.94
    ﹑
    2.84
    ",
    2.80
     köln
    2.78
     Juillet
    2.72
    with
    2.67
     chcesz
    2.64
    ',
    2.63
    Activations Density 0.004%

    No Known Activations