© 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. 33452
    Prev
    Next
    INDEX
    Explanations

    identical, same, equivalent

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

    The neuron activates on numeric values (tokens representing numbers, including integers and decimals).

    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
     repetir
    -0.86
    strnc
    -0.85
     pureza
    -0.84
    loat
    -0.81
     distinguishes
    -0.79
    讶
    -0.77
    事例
    -0.76
     مؤرشف
    -0.76
     takto
    -0.76
    strncmp
    -0.73
    POSITIVE LOGITS
     equivalent
    1.32
     functionally
    1.10
     results
    1.08
    equivalent
    1.05
     сути
    1.00
     ultimately
    0.98
     Equivalent
    0.95
     коне
    0.94
    Equivalent
    0.91
     équi
    0.89
    Activations Density 0.077%

    No Known Activations