© 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. 72365
    Prev
    Next
    INDEX
    Explanations

    each of something

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

    The neuron responds to numeric expressions and quantities (digits, numbers, and numeric tokens).

    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
     and
    -0.98
     or
    -0.88
    existsSync
    -0.84
     кожу
    -0.82
     ďal
    -0.82
    ethers
    -0.76
     while
    -0.76
    msleep
    -0.76
     like
    -0.76
     no
    -0.76
    POSITIVE LOGITS
     each
    1.60
    each
    1.43
     chacune
    1.29
     EACH
    1.26
    EACH
    1.21
    Each
    1.17
     каждой
    1.14
     chacun
    1.06
     каждого
    1.06
    それぞれの
    1.05
    Activations Density 0.256%

    No Known Activations