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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 906
    Prev
    Next
    INDEX
    Explanations

    date and government information

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

    This neuron detects numeric identifiers and classification tokens in military unit or vessel designations (e.g. regiment numbers, U-boat model numbers, Type VIIC codes).

    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
     Schwä
    -0.79
     Oregon
    -0.74
     Geden
    -0.72
     enf
    -0.71
     Grün
    -0.71
    ер
    -0.71
     ください
    -0.71
     Ketten
    -0.70
     британ
    -0.70
    век
    -0.70
    POSITIVE LOGITS
     Ergänzung
    0.79
     RSI
    0.78
     Fest
    0.76
    mota
    0.76
    rät
    0.74
     Mussolini
    0.73
     rapist
    0.72
     heron
    0.72
    zic
    0.71
    amous
    0.71
    Activations Density 0.029%

    No Known Activations