© 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. 20025
    Prev
    Next
    INDEX
    Explanations

    sodden streets, forcible transfer

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

    The neuron fires on any occurrence of the character sequence “sob” (i.e. tokens containing “sob”).

    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
    菝
    -3.22
    恫
    -2.72
    
    -2.63
    Ⲉ
    -2.59
     is
    -2.59
    銩
    -2.52
    菀
    -2.47
    一八
    -2.47
    𓆜
    -2.45
    沇
    -2.41
    POSITIVE LOGITS
    ’
    3.61
    1
    3.53
    ↵↵
    3.38
    та
    3.14
    5
    2.78
    2
    2.70
    7
    2.67
    s
    2.61
    3
    2.59
    8
    2.58
    Activations Density 0.001%

    No Known Activations