© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85491
    Prev
    Next
    INDEX
    Explanations

    squamous cell carcinoma

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

    descriptions of a person's nationality or ethnic origin.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on explicit time‐of‐day expressions (e.g., “local time,” time‐zone notations, and similar clock‐time mentions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    就连
    -1.66
    甚至
    -1.59
    也是
    -1.58
    when
    -1.58
    ly
    -1.52
     nawet
    -1.51
    ᵢ
    -1.45
    ⦊
    -1.44
     даже
    -1.44
     before
    -1.43
    POSITIVE LOGITS
    upb
    1.54
     realmente
    1.54
     vooral
    1.53
     понравилось
    1.46
     then
    1.43
    sach
    1.41
    emily
    1.40
    gucci
    1.39
     nové
    1.39
     umožňuje
    1.38
    Activations Density 0.074%

    No Known Activations