© 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. 119674
    Prev
    Next
    INDEX
    Explanations

    video game titles

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

    video game titles and franchises.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    ).
    -1.78
    多く
    -1.63
    ogue
    -1.58
    [
    -1.57
    </strong>
    -1.56
     includes
    -1.55
    ities
    -1.55
    尤其是
    -1.48
    room
    -1.45
     amargo
    -1.45
    POSITIVE LOGITS
     to
    1.59
    Shopify
    1.58
     convite
    1.48
    耽
    1.46
     Inſ
    1.46
     Then
    1.41
     indivíduo
    1.37
    聍
    1.37
    ))->
    1.31
     Affaires
    1.31
    Activations Density 0.026%

    No Known Activations