© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75705
    Prev
    Next
    INDEX
    Explanations

    university assessments

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

    The neuron fires on tokens made up primarily of uppercase letters and digits—e.g. acronyms, version numbers, and other formal identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    握
    -0.77
    rotz
    -0.77
     thạch
    -0.71
    manuelle
    -0.71
     উ
    -0.69
    lagio
    -0.68
     récolte
    -0.67
     inducted
    -0.67
     buckwheat
    -0.66
    tcb
    -0.66
    POSITIVE LOGITS
     Semester
    0.94
     semester
    0.92
     QUESTION
    0.80
    enthal
    0.77
    ///</
    0.77
    venues
    0.77
     CONTIN
    0.76
    зовать
    0.75
     milliards
    0.75
    fabs
    0.74
    Activations Density 0.011%

    No Known Activations