© 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. 104207
    Prev
    Next
    INDEX
    Explanations

    various languages or specific phrases

    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
    laszt
    -2.00
     fortfarande
    -1.98
     olika
    -1.87
    om
    -1.84
    how
    -1.77
    ︲
    -1.77
    }
    -1.77
    ay
    -1.70
     verkligen
    -1.70
    اً
    -1.68
    POSITIVE LOGITS
     and
    2.27
    hilangan
    1.55
     sufri
    1.50
     aña
    1.43
    ném
    1.42
     tijden
    1.41
    dö
    1.41
    ikkert
    1.40
    pente
    1.40
     limpi
    1.40
    Activations Density 0.018%

    No Known Activations