© 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. 65732
    Prev
    Next
    INDEX
    Explanations

    Tobacco Industry

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

    The neuron activates on tokens that are numeric or alphanumeric designators (i.e. any token containing digits).

    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
    🇦
    -0.80
    aerop
    -0.78
    Kurt
    -0.77
     airborne
    -0.76
    voet
    -0.75
     helicopter
    -0.75
    př
    -0.74
     detects
    -0.73
    idopsis
    -0.72
    iction
    -0.71
    POSITIVE LOGITS
    ラー
    0.77
     PROTECT
    0.75
    Damien
    0.74
    toilet
    0.73
    ENAS
    0.72
     Cecil
    0.71
     Olin
    0.71
    getField
    0.70
     Ribs
    0.68
    filé
    0.68
    Activations Density 0.019%

    No Known Activations