© 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. 65568
    Prev
    Next
    INDEX
    Explanations

    languages like Spanish, Portuguese, French

    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
     vierge
    -0.85
    Finale
    -0.82
    และ
    -0.82
     של
    -0.80
     और
    -0.78
    candles
    -0.76
    却是
    -0.75
     capac
    -0.74
    Tas
    -0.74
     monter
    -0.74
    POSITIVE LOGITS
    accro
    0.82
    during
    0.81
    在美国
    0.81
     gegenüber
    0.81
    Muito
    0.79
     počas
    0.78
    Abraços
    0.78
    usure
    0.78
    เค้า
    0.77
    according
    0.76
    Activations Density 0.026%

    No Known Activations