© 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. 66062
    Prev
    Next
    INDEX
    Explanations

    languages and symbols

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

    This neuron detects standalone numeric tokens (especially answer‐choice labels and numeric values) in the text.

    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
    featuring
    -1.00
    deutung
    -1.00
    が違う
    -1.00
    埂
    -0.95
    
    -0.94
     ",";
    -0.92
     praktis
    -0.91
    ptid
    -0.91
    intellij
    -0.91
    Ⅎ
    -0.90
    POSITIVE LOGITS
    0.87
    T
    0.86
     sudor
    0.81
     forgot
    0.77
    řeba
    0.77
     пот
    0.77
    DESC
    0.77
     بالم
    0.76
     pendant
    0.76
    ͎
    0.76
    Activations Density 0.003%
    No Known Activations