© 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. 9269
    Prev
    Next
    INDEX
    Explanations

    myopia, hiatus, HTC, Abhijit, DataLoader

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

    The neuron responds to occurrences of the substring “opia,” i.e. mentions of myopia or related myopia forms.

    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
    '));
    -2.67
    ྜ
    -2.48
    ,”
    -2.47
    ;
    -2.47
    ”:
    -2.45
    沇
    -2.44
    禵
    -2.38
     mendapatkan
    -2.38
    ൎ
    -2.33
    ();
    -2.30
    POSITIVE LOGITS
     作り方
    2.34
    ين
    2.34
     MUCH
    2.22
    鏟
    2.19
     eigener
    2.19
     ofthe
    2.17
    是可以
    2.17
     använder
    2.14
    厮
    2.14
    榈
    2.11
    Activations Density 0.016%

    No Known Activations