© 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. 34906
    Prev
    Next
    INDEX
    Explanations

    even, multiple, or divisible

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

    The neuron fires on numeric expressions and related arithmetic terms (digits, “even,” “multiple,” “divisible,” etc.).

    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
    аз
    -1.02
     Harden
    -0.91
    ✞
    -0.91
     individually
    -0.90
     whether
    -0.90
    tains
    -0.87
    Italic
    -0.87
    instead
    -0.87
     концеп
    -0.86
     ainsi
    -0.85
    POSITIVE LOGITS
     other
    1.29
    ICIAN
    1.05
    役割
    1.01
    假的
    1.00
    ложении
    0.99
     babi
    0.98
    ==""){
    0.98
     verwij
    0.98
     automatico
    0.97
     trattato
    0.97
    Activations Density 0.014%

    No Known Activations