© 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. 34-GEMMASCOPE-RES-131K
    7. 60500
    Prev
    Next
    INDEX
    Explanations

    unsigned long long

    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
     wild
    -0.92
    Wild
    -0.91
     Wild
    -0.90
    wild
    -0.89
     leop
    -0.82
     Wilder
    -0.79
     WILD
    -0.78
    opcao
    -0.77
    cinoma
    -0.77
    مساعدة
    -0.76
    POSITIVE LOGITS
    dll
    1.48
     ILL
    1.45
    LL
    1.44
     LL
    1.42
    pll
    1.41
    cll
    1.39
     BLL
    1.34
    PLL
    1.34
    oll
    1.32
     ELL
    1.31
    Activations Density 0.043%

    No Known Activations