© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84173
    Prev
    Next
    INDEX
    Explanations

    FROM THE state

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

    The neuron remains inactive on all tokens shown and thus does not detect any specific pattern in these examples.

    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
    '
    -4.94
    s
    -3.22
     "
    -3.16
     This
    -2.53
     are
    -2.53
     comenz
    -2.50
     '
    -2.33
    ,"
    -2.30
    ''
    -2.20
     generando
    -2.20
    POSITIVE LOGITS
    ᭝
    3.22
    柃
    2.95
    胧
    2.86
    しましたが
    2.72
    to
    2.70
    巔
    2.69
    一个月
    2.61
     να
    2.52
    几分
    2.52
    เพื่อ
    2.44
    Activations Density 0.003%

    No Known Activations