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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49565
    Prev
    Next
    INDEX
    Explanations

    entities, working, population, PC

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

    The neuron selectively activates on numeric tokens (numbers and numeric sequences).

    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
     Kenn
    -0.80
     McM
    -0.76
     undisclosed
    -0.75
    illets
    -0.75
    rcl
    -0.68
    FUND
    -0.67
     продав
    -0.67
    勤
    -0.67
     diagonally
    -0.67
    proses
    -0.66
    POSITIVE LOGITS
    циональный
    0.72
     информацию
    0.69
    efd
    0.69
     Misty
    0.68
    ena
    0.68
     Pressed
    0.68
    werk
    0.66
     II
    0.66
    afar
    0.65
    ーと
    0.64
    Activations Density 0.028%

    No Known Activations