© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100955
    Prev
    Next
    INDEX
    Explanations

    Warhol, themes, Q, Newsletter, South

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

    This neuron flags uncommon or foreign tokens—i.e. rare words (including proper names like “Warhol,” specialized terms like “themes,” and non-Latin words such as Japanese/Chinese tokens).

    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
    and
    -2.48
     keterampilan
    -2.36
    可以
    -2.28
     kesadaran
    -2.28
    at
    -2.28
     và
    -2.20
    q
    -2.20
    龗
    -2.19
     Очень
    -2.17
     ponsel
    -2.17
    POSITIVE LOGITS
    的吧
    2.72
    鸶
    2.55
    的了
    2.45
    栒
    2.25
    ,
    2.20
    鈊
    2.20
    鹂
    2.16
    想了想
    2.13
    that
    2.08
    animals
    2.05
    Activations Density 0.000%

    No Known Activations