© 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. 22-GEMMASCOPE-RES-131K
    7. 26398
    Prev
    Next
    INDEX
    Explanations

    categories of content

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

    The neuron fires on visible category or section labels (e.g. “Lifestyle,” “Restaurants,” “Fashion,” etc.) indicating the document’s topical category.

    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
     regia
    -1.33
     both
    -1.19
    </b>
    -1.15
    N
    -1.12
     their
    -1.05
     impressive
    -1.05
    …..
    -0.98
    ….
    -0.98
     festa
    -0.97
     unusual
    -0.95
    POSITIVE LOGITS
     circunstancia
    1.41
     行っ
    1.36
    がありますが
    1.31
    踌
    1.26
    もあって
    1.23
     réinitial
    1.23
    generally
    1.22
    鸩
    1.22
     actualización
    1.18
     araña
    1.18
    Activations Density 0.052%

    No Known Activations