© 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. 34178
    Prev
    Next
    INDEX
    Explanations

    each respectively

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

    The neuron is looking for numeric literals (numbers or numeric constants) 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_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
     it
    -1.45
     its
    -1.39
     this
    -1.16
     two
    -1.00
    :
    -0.98
    着一个
    -0.96
    它
    -0.96
     a
    -0.96
    ;
    -0.95
    [
    -0.95
    POSITIVE LOGITS
     jeweils
    1.34
     jejich
    1.13
     chacun
    1.12
    respectively
    1.10
     fiecare
    1.09
     pokoj
    1.07
     jeweiligen
    1.03
    respective
    1.02
    Ils
    1.02
     chacune
    1.02
    Activations Density 0.007%

    No Known Activations