© 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. 41613
    Prev
    Next
    INDEX
    Explanations

    DIS and succes

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

    The neuron activates on tokens containing the uppercase substring “DIS,” e.g. as part of acronyms or identifiers.

    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
    s
    -3.83
    h
    -3.16
    ),
    -3.16
    </td>
    -3.02
    .,
    -2.77
     \%$
    -2.75
    ↵↵
    -2.72
    «
    -2.69
    ?
    -2.69
    .
    -2.69
    POSITIVE LOGITS
    寕
    3.11
    𖣘
    2.83
     uſed
    2.77
    蹓
    2.73
    НЫЕ
    2.69
     fédé
    2.64
    樒
    2.63
     باسلام
    2.61
     短发
    2.59
    ଢ
    2.55
    Activations Density 0.007%

    No Known Activations