© 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. 58973
    Prev
    Next
    INDEX
    Explanations

    copyright statements in code

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

    This neuron fires on document-level metadata or section-header keywords (e.g. headings like “Copyright,” “From,” “Activity,” or “Symptoms”).

    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
     poised
    -0.70
    litude
    -0.70
     encephal
    -0.69
     занимает
    -0.68
     pendapatan
    -0.68
    corbic
    -0.67
    يره
    -0.66
     PLAINT
    -0.66
     megs
    -0.65
     подчер
    -0.65
    POSITIVE LOGITS
     entry
    0.79
    це
    0.78
    printf
    0.76
    inerario
    0.76
    ynth
    0.73
     мень
    0.72
    eseen
    0.72
    nergie
    0.71
    treated
    0.71
    ianos
    0.71
    Activations Density 0.019%

    No Known Activations