© 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. 10-GEMMASCOPE-RES-131K
    7. 44441
    Prev
    Next
    INDEX
    Explanations

    Orlando limo service

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

    The neuron fires on long punctuation-based dividers or section breaks (e.g. em-dashes, divider lines, and other formatting separators).

    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
    錞
    -2.48
    ໊
    -2.39
    ѣмъ
    -2.30
    ༵
    -2.27
    蠖
    -2.25
     verhind
    -2.19
    "،
    -2.16
    쨩
    -2.14
    俢
    -2.09
    )',
    -2.08
    POSITIVE LOGITS
    ましたが
    2.19
    viembre
    2.11
    應該
    2.08
     に関する
    2.05
    详解
    1.95
     だけ
    1.88
     letzte
    1.88
    ;
    1.88
     criter
    1.86
     have
    1.84
    Activations Density 0.000%

    No Known Activations