© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47904
    Prev
    Next
    INDEX
    Explanations

    when and case

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

    The neuron primarily detects numeric tokens (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
     during
    -0.98
    During
    -0.96
     before
    -0.90
    Each
    -0.89
    before
    -0.85
    Before
    -0.83
    during
    -0.82
     beneath
    -0.80
     after
    -0.79
    ××
    -0.77
    POSITIVE LOGITS
    WHEN
    1.02
     WHEN
    0.93
    corrected
    0.88
    microbial
    0.81
    ğinde
    0.79
    paramInt
    0.76
    splitter
    0.75
     cuándo
    0.74
     whe
    0.73
    lity
    0.73
    Activations Density 0.022%

    No Known Activations