© 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. 86950
    Prev
    Next
    INDEX
    Explanations

    King, Justice, names, places, years

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

    The neuron strongly activates on multi‐digit numeric tokens—especially four‐digit numbers like years or reference numbers.

    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
     fifties
    -0.84
     postwar
    -0.82
    dismiss
    -0.81
     Eisenhower
    -0.77
     cân
    -0.75
     oscu
    -0.75
     mid
    -0.70
     tug
    -0.69
    گونه
    -0.69
    mid
    -0.67
    POSITIVE LOGITS
    zzo
    0.82
    gameserver
    0.79
     Axiom
    0.77
    隔壁
    0.75
    ujących
    0.74
    aterin
    0.74
     emisión
    0.73
     AAS
    0.72
     SIC
    0.71
     Veld
    0.71
    Activations Density 0.070%

    No Known Activations