© 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. 78934
    Prev
    Next
    INDEX
    Explanations

    version 1.0

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

    The neuron fires primarily on numeric tokens (sequences of digits).

    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
    ely
    -0.79
     ಜ
    -0.77
    appelle
    -0.73
     entra
    -0.71
    jdons
    -0.71
     disputes
    -0.70
     zuständig
    -0.68
     cue
    -0.68
    фере
    -0.68
    ESTA
    -0.67
    POSITIVE LOGITS
    Ұ
    0.76
     byen
    0.76
    uname
    0.75
    ði
    0.72
     ***!
    0.72
    Evans
    0.70
    cele
    0.69
     ladle
    0.69
     Riche
    0.68
    iali
    0.68
    Activations Density 0.021%

    No Known Activations