© 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. 22-GEMMASCOPE-RES-131K
    7. 98325
    Prev
    Next
    INDEX
    Explanations

    this followed by specific content

    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_22/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
    ここは
    -1.08
    雰囲気が
    -1.02
     mentre
    -1.02
     need
    -1.01
    alors
    -0.99
    いけない
    -0.99
    uxedo
    -0.98
     maniera
    -0.96
    Пря
    -0.96
    雰囲
    -0.95
    POSITIVE LOGITS
    :
    1.11
    هایی
    1.04
     two
    1.03
     Ву
    0.98
    ==='
    0.96
     aldri
    0.95
     suyo
    0.93
    /***
    0.92
     a
    0.91
     ogran
    0.91
    Activations Density 0.085%

    No Known Activations