© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30604
    Prev
    Next
    INDEX
    Explanations

    special characters followed by uppercase letters

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

    The neuron is triggered by a caret (^) immediately followed by a single uppercase letter, i.e. superscript-style reference markers.

    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
    ۹
    -1.01
     упаковки
    -0.97
    jure
    -0.97
     Béla
    -0.92
    近期
    -0.91
    XmlRootElement
    -0.91
    ม
    -0.91
    撰
    -0.91
    写真
    -0.90
    登录
    -0.90
    POSITIVE LOGITS
     객체
    1.05
    됬
    1.04
    giacca
    0.98
     thậm
    0.96
     equipamiento
    0.94
     Anbieter
    0.93
     C
    0.91
     disminu
    0.90
     D
    0.90
     A
    0.89
    Activations Density 0.072%

    No Known Activations