© 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. 22-GEMMASCOPE-RES-131K
    7. 129684
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric literals, i.e. tokens representing numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mathematical variables and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     تصریح
    -0.84
    机关
    -0.81
     compositeur
    -0.79
     certamente
    -0.79
    Ố
    -0.78
    もあって
    -0.78
     cherchez
    -0.77
     indulgence
    -0.77
     rood
    -0.76
     jogadores
    -0.76
    POSITIVE LOGITS
     or
    1.21
     as
    1.20
     that
    1.02
     this
    0.95
     every
    0.88
    jws
    0.88
    ％
    0.87
    Второй
    0.85
     which
    0.85
     meraih
    0.85
    Activations Density 0.018%

    No Known Activations