© 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. 34890
    Prev
    Next
    INDEX
    Explanations

    list items or code snippets

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

    The neuron activates on numeric tokens—digits, numbers, and numeric expressions like fractions.

    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
     that
    -0.93
     very
    -0.84
     most
    -0.82
    كونات
    -0.79
    最後は
    -0.78
     ultimately
    -0.77
     because
    -0.77
    坡
    -0.77
    現在は
    -0.74
    Causas
    -0.74
    POSITIVE LOGITS
     others
    1.07
     tomorrow
    1.06
    others
    0.97
    
    0.93
    रा
    0.91
     lim
    0.90
    acterium
    0.90
    ഷ
    0.90
    onation
    0.89
    उ
    0.89
    Activations Density 0.010%

    No Known Activations