© 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. 65531
    Prev
    Next
    INDEX
    Explanations

    prefix detection

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

    The neuron fires primarily on numeric tokens or token sequences containing digits (i.e. 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_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
    Gebruik
    -0.87
    Новая
    -0.84
     محفوظ
    -0.81
    ıklı
    -0.80
    こちらは
    -0.80
     Carmelo
    -0.77
     potrebbe
    -0.77
     قبول
    -0.74
     Jy
    -0.73
     Melon
    -0.73
    POSITIVE LOGITS
     prefix
    0.97
    Prefix
    0.89
     MEX
    0.81
     Takahashi
    0.80
     beauty
    0.80
     stalls
    0.79
     sequences
    0.78
     Chef
    0.78
     Query
    0.77
    prefix
    0.77
    Activations Density 0.036%

    No Known Activations