© 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. 110730
    Prev
    Next
    INDEX
    Explanations

    success rate

    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
     dezelve
    -1.88
     eres
    -1.59
     eenig
    -1.56
     verſ
    -1.53
     mostrando
    -1.53
    tığı
    -1.52
     eenige
    -1.52
     eenen
    -1.45
    </h3>
    -1.43
     naam
    -1.41
    POSITIVE LOGITS
     sebelum
    1.71
     Already
    1.59
    機場
    1.56
    覽
    1.56
     Often
    1.55
    </b>
    1.55
    Also
    1.53
    𓋼
    1.52
     Sadly
    1.49
     raggiunto
    1.48
    Activations Density 0.039%

    No Known Activations