© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84567
    Prev
    Next
    INDEX
    Explanations

    footnote markers and references

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

    The neuron detects footnote markers and reference anchors (e.g. “Footnotes,” “footnote,” superscript numbers, and related labels).

    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
     or
    -0.94
     или
    -0.78
     Thou
    -0.75
    nius
    -0.74
    ctivity
    -0.74
     snippetHide
    -0.74
    identiality
    -0.73
     and
    -0.72
    сер
    -0.71
     between
    -0.71
    POSITIVE LOGITS
     supers
    0.92
     referrer
    0.84
     Supers
    0.79
     Fortun
    0.79
     DISEASES
    0.77
     foot
    0.77
     superstar
    0.76
     Lieber
    0.76
    uParam
    0.75
    的做法
    0.75
    Activations Density 0.208%

    No Known Activations