© 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. 91513
    Prev
    Next
    INDEX
    Explanations

    peace herring No

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

    The neuron activates on numeric tokens (years, volume and page numbers, section references, etc.).

    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
    arbol
    -0.73
     Bertram
    -0.71
     Devils
    -0.71
    tease
    -0.71
    richText
    -0.71
    Snail
    -0.70
     richting
    -0.69
     conseillers
    -0.69
    CAPITAL
    -0.68
    getreten
    -0.68
    POSITIVE LOGITS
    Ger
    0.77
     Za
    0.77
    Za
    0.75
    斐
    0.71
     Έ
    0.71
    وث
    0.69
     Ger
    0.68
     CT
    0.68
     jewellery
    0.68
     BO
    0.67
    Activations Density 0.072%

    No Known Activations