© 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. 44298
    Prev
    Next
    INDEX
    Explanations

    used as a parameter or variable

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

    The neuron consistently activates on the word “target,” i.e. it’s keyed to detect the token “target” wherever it appears.

    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
    atação
    -1.95
     \&
    -1.86
     halbe
    -1.84
     особенно
    -1.78
    ませんが
    -1.76
    璠
    -1.74
    小さ
    -1.73
     ktorá
    -1.72
     '
    -1.71
     maravill
    -1.70
    POSITIVE LOGITS
    d
    2.42
    ൎ
    2.41
    饃
    2.33
    漼
    2.30
    
    2.28
    禵
    2.23
    ѣмъ
    2.22
    Ꮫ
    2.22
    剽
    2.19
    尨
    2.17
    Activations Density 0.018%

    No Known Activations