© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102395
    Prev
    Next
    INDEX
    Explanations

    sepsis classics tanker Dixie Hanks Dak

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

    The neuron fires on capitalized tokens that signal proper names or titles (e.g. named entities and headings).

    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
    ाउनलोड
    -2.58
     weirdly
    -2.44
     Eigentü
    -2.42
     seemingly
    -2.41
     oddly
    -2.36
    ڧ
    -2.34
     cheery
    -2.34
    蘩
    -2.28
     Geräten
    -2.27
    ​.
    -2.25
    POSITIVE LOGITS
    哂
    2.48
     avec
    2.31
     wichtige
    2.23
     与
    2.16
     TO
    2.14
     consider
    2.14
    有些
    2.14
    ../../
    2.14
    鼉
    2.03
     You
    2.02
    Activations Density 0.008%

    No Known Activations