© 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. 10-GEMMASCOPE-RES-131K
    7. 103369
    Prev
    Next
    INDEX
    Explanations

    NB-IoT, NB, neuroblastoma

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

    The neuron detects abbreviation "NB" (and sometimes "NBH") in technical and scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    鈇
    -2.95
    雰
    -2.64
    芣
    -2.61
    鉝
    -2.61
     丁目
    -2.53
     {
    -2.47
    ي
    -2.44
    洇
    -2.44
    媜
    -2.39
    ڧ
    -2.39
    POSITIVE LOGITS
    or
    2.86
    you
    2.67
    釹
    2.45
    衛隊
    2.38
    咈
    2.34
    ies
    2.31
    ية
    2.25
     horrors
    2.22
    力和
    2.22
    偏偏
    2.19
    Activations Density 0.005%

    No Known Activations