© 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. 129945
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric literals (integer values) embedded anywhere in the code or markup.

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

    microsomal, copyright, code comments

    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
    ּוֹ
    -1.35
     that
    -1.29
     włos
    -1.23
    ַּ
    -1.23
    ִּ
    -1.10
    べし
    -1.08
     oreilles
    -1.07
     AnyObject
    -1.06
     the
    -1.05
    forall
    -1.05
    POSITIVE LOGITS
     another
    1.40
    ׇ
    1.30
     even
    1.28
     also
    1.16
    Another
    1.05
     נוסף
    1.03
     only
    1.02
     besonders
    0.98
     at
    0.98
    мма
    0.96
    Activations Density 0.001%

    No Known Activations