© 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. 353
    Prev
    Next
    INDEX
    Explanations

    physical punishment

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

    The neuron fires on multi‐digit numeric sequences (long numbers) 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
    capsulation
    -0.76
    ogeneity
    -0.75
     mountains
    -0.73
    phinx
    -0.72
     activiteiten
    -0.71
    륜
    -0.71
     семе
    -0.71
    醮
    -0.71
    認め
    -0.71
    ッと
    -0.71
    POSITIVE LOGITS
     whipping
    2.56
     whip
    2.44
     whips
    2.30
     whipped
    2.27
     corporal
    2.14
     Whip
    2.06
    whip
    1.97
    Whip
    1.95
    鞭
    1.81
     beat
    1.73
    Activations Density 0.018%

    No Known Activations