© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84550
    Prev
    Next
    INDEX
    Explanations

    absence or negation

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

    This neuron detects numeric tokens (standalone numbers or digit sequences) 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_34/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
    тування
    -0.76
    тик
    -0.75
    يي
    -0.73
    嫔
    -0.73
    लग
    -0.73
    keypress
    -0.72
    пуска
    -0.71
     zároveň
    -0.71
    enez
    -0.70
    κει
    -0.69
    POSITIVE LOGITS
     none
    9.00
     None
    7.28
    none
    7.16
    None
    7.09
    NONE
    5.94
     NONE
    5.72
     ninguno
    5.06
     ninguna
    3.72
     nenhum
    3.56
     nenhuma
    3.28
    Activations Density 0.197%

    No Known Activations