© 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. 54116
    Prev
    Next
    INDEX
    Explanations

    extraterrestrial abduction or visitation

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

    The neuron detects proper‐name and numeric tokens (e.g. titles, personal names, years, counts).

    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
     ${({
    -1.02
    laszt
    -0.91
    jaardag
    -0.90
    bner
    -0.89
    เลือก
    -0.87
     profissional
    -0.87
     resourceCulture
    -0.85
     фла
    -0.84
    IGN
    -0.84
    Argb
    -0.82
    POSITIVE LOGITS
     Bewußt
    1.12
    镯
    1.01
    recovered
    0.93
     anstatt
    0.91
     mantienen
    0.90
    empla
    0.88
    Tic
    0.87
    手镯
    0.86
     technologies
    0.85
     vektör
    0.85
    Activations Density 0.012%

    No Known Activations