© 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. 10-GEMMASCOPE-RES-131K
    7. 10416
    Prev
    Next
    INDEX
    Explanations

    numbers and code snippets

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

    numeric literals with decimal points, particularly when followed by specific formatting or delimiters in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron activates on numeric literals (especially floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Even
    -2.31
     If
    -2.25
    Two
    -2.19
    All
    -2.09
    After
    -2.03
     EVERY
    -2.00
    Despite
    -1.99
     all
    -1.99
    Though
    -1.98
    Just
    -1.98
    POSITIVE LOGITS
     misschien
    2.13
    secuencias
    2.03
    を購入
    1.96
     ridiculously
    1.93
    揠
    1.92
     usados
    1.92
    
    1.91
     decidedly
    1.90
     nowej
    1.89
     quintessential
    1.87
    Activations Density 0.007%

    No Known Activations