© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57828
    Prev
    Next
    INDEX
    Explanations

    consisting of

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

    The neuron primarily fires on numeric constants (multi‐digit numbers) in the text.

    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
    iclo
    -0.72
    piers
    -0.69
    
    -0.69
     recente
    -0.68
     Steuer
    -0.68
    ľ
    -0.68
     alho
    -0.67
    IMM
    -0.67
     movimenta
    -0.66
    firmasi
    -0.65
    POSITIVE LOGITS
    ншот
    0.68
    Travelling
    0.68
     Oakley
    0.68
     came
    0.68
     went
    0.67
    讀書
    0.66
    Over
    0.66
     тер
    0.65
     أش
    0.65
    Ter
    0.64
    Activations Density 0.059%

    No Known Activations