© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90713
    Prev
    Next
    INDEX
    Explanations

    database execution context

    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_34/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
     but
    -1.42
     rağmen
    -1.29
     to
    -1.26
    yoshi
    -1.10
     десять
    -1.02
     nascita
    -1.01
    不肯
    -1.01
    愉
    -1.00
    了一会儿
    -1.00
    ebly
    -1.00
    POSITIVE LOGITS
    擷
    1.28
    並不是
    1.23
    中略
    1.23
    灃
    1.17
    えっ
    1.16
    関連記事
    1.13
     scary
    1.12
     certainement
    1.10
     pratiquement
    1.09
     consulté
    1.08
    Activations Density 0.043%

    No Known Activations