© 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. 22-GEMMASCOPE-RES-131K
    7. 39393
    Prev
    Next
    INDEX
    Explanations

    author names

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

    The neuron never activates on any part of these scientific document excerpts, i.e. it does not detect or respond to any tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     what
    -1.26
     áreas
    -1.19
    ⩽
    -1.16
    );"
    -1.12
     variar
    -1.12
     one
    -1.05
    怎么
    -1.02
    arté
    -1.01
     ),
    -1.00
    ！(
    -0.98
    POSITIVE LOGITS
    </b>
    1.29
    為に
    1.12
    vantaged
    1.11
     مصرى
    1.09
    晴れ
    1.05
     مانند
    1.01
    </i>
    0.99
    essayer
    0.99
    蹩
    0.98
     säga
    0.98
    Activations Density 0.001%

    No Known Activations