© 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. 112414
    Prev
    Next
    INDEX
    Explanations

    now and current situation

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

    The neuron primarily detects numeric tokens (digits and numeric values, including integers and decimals).

    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
     pregunt
    -1.70
     They
    -1.60
    の方は
    -1.51
    なども
    -1.50
     inicialmente
    -1.49
     escuchar
    -1.48
    However
    -1.46
    用の
    -1.45
     så
    -1.41
    Chennai
    -1.41
    POSITIVE LOGITS
     it
    2.13
    以上です
    1.74
    $
    1.73
    怎么说
    1.67
     frankly
    1.66
     Diſ
    1.61
    ,’”
    1.61
    茀
    1.59
    完成です
    1.59
     curiously
    1.57
    Activations Density 0.009%

    No Known Activations