© 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. 10-GEMMASCOPE-RES-131K
    7. 67959
    Prev
    Next
    INDEX
    Explanations

    number 2

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

    The neuron consistently fires on the standalone digit “2,” marking occurrences of the number two 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_10/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
     öns
    -1.59
     restauración
    -1.57
    fertigen
    -1.53
    ejemplo
    -1.51
     zimowa
    -1.50
     olika
    -1.47
     préstamos
    -1.47
     véritables
    -1.46
    𒊹
    -1.45
     camiones
    -1.42
    POSITIVE LOGITS
     still
    1.99
     be
    1.75
     there
    1.63
     think
    1.62
     find
    1.55
     then
    1.53
     time
    1.51
     will
    1.50
     again
    1.48
     we
    1.46
    Activations Density 0.019%

    No Known Activations