© 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. 69645
    Prev
    Next
    INDEX
    Explanations

    everytime, тогда, まで

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

    The neuron responds to non-English scripts and characters (e.g. Japanese or Cyrillic tokens and special punctuation like wave-dashes).

    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
    "
    -3.72
    }$
    -3.64
    D
    -2.81
     '
    -2.70
    {
    -2.66
    ,"
    -2.61
    );
    -2.59
    -2.56
    ,;
    -2.56
    s
    -2.52
    POSITIVE LOGITS
    i
    3.08
    蘩
    3.06
    亊
    2.81
     beijo
    2.80
    淠
    2.72
     juſ
    2.69
    骜
    2.69
     bileklik
    2.67
    ستارهای
    2.64
    
    2.64
    Activations Density 0.002%

    No Known Activations