© 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. 22-GEMMASCOPE-RES-131K
    7. 128207
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric literals (digit sequences) in the text.

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

    statement terminators and code enders

    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
    omentos
    -0.89
     Puppies
    -0.88
    Tja
    -0.87
    Ramen
    -0.85
    などは
    -0.81
    くに
    -0.79
     APART
    -0.78
    🧶
    -0.78
     kropp
    -0.78
    Groet
    -0.78
    POSITIVE LOGITS
     Then
    1.09
     then
    0.94
    Then
    0.92
    リゾート
    0.81
    riam
    0.81
     everyone
    0.79
    URING
    0.79
    volent
    0.79
     χρό
    0.78
    Sound
    0.78
    Activations Density 0.006%

    No Known Activations