© 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. 104773
    Prev
    Next
    INDEX
    Explanations

    technical terms with descriptions

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

    plural nouns in technical or academic contexts, particularly when discussing multiple items, components, or categories within a system or study.

    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
    ());
    -1.23
     boneco
    -1.21
     and
    -1.20
     walaupun
    -1.16
    bouncycastle
    -1.14
     conclusión
    -1.11
     båda
    -1.09
    即便
    -1.09
     vulga
    -1.08
    </i>
    -1.07
    POSITIVE LOGITS
     namely
    1.49
     you
    1.21
    皤
    1.19
    入荷
    1.09
     findest
    1.09
    好啊
    1.07
    ICIAS
    1.06
    㐂
    1.05
    seits
    1.04
    vitt
    1.04
    Activations Density 0.270%

    No Known Activations