© 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. 75099
    Prev
    Next
    INDEX
    Explanations

    discrete units or collections

    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
     to
    -1.22
    ラの
    -0.94
    스터
    -0.91
     bakom
    -0.90
    checs
    -0.88
     liksom
    -0.88
     omin
    -0.87
     are
    -0.86
    rité
    -0.83
    gig
    -0.82
    POSITIVE LOGITS
     using
    1.05
     wrze
    1.04
     without
    1.03
     iulie
    1.01
    ₀
    0.99
    }
    0.98
     используя
    0.98
     septembrie
    0.97
    resizeMode
    0.97
    Cuáles
    0.94
    Activations Density 0.138%

    No Known Activations