© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41219
    Prev
    Next
    INDEX
    Explanations

    all that followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    圌
    -1.87
    鹇
    -1.79
    鲧
    -1.68
    鉏
    -1.63
    的模样
    -1.63
    </h3>
    -1.59
    ted
    -1.56
     다음
    -1.56
     estadounid
    -1.55
    ︕
    -1.53
    POSITIVE LOGITS
     greateſt
    1.72
    衎
    1.48
    </b>
    1.45
    <bos>
    1.44
    世间
    1.42
    ıda
    1.40
     junho
    1.38
    dbContext
    1.34
    XXIV
    1.33
    Analyte
    1.30
    Activations Density 0.009%

    No Known Activations