© 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. 43692
    Prev
    Next
    INDEX
    Explanations

    follows or precedes specific patterns

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

    The neuron selectively activates on mentions of “tote” (and its variants like “toting” or product names containing “Tote”), i.e. references to tote bags.

    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
    b
    -2.47
    .
    -2.39
    j
    -2.20
    h
    -2.19
    il
    -2.13
    g
    -2.13
    ri
    -2.11
    Таким
    -2.09
     этому
    -2.08
     dainty
    -2.08
    POSITIVE LOGITS
    萏
    2.33
    greja
    2.28
    这事
    2.27
    してない
    2.20
    鲼
    2.19
    䨻
    2.16
    trailer
    2.13
    喾
    2.08
    𓁹
    2.06
    猡
    2.06
    Activations Density 0.001%

    No Known Activations