© 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. 22-GEMMASCOPE-RES-131K
    4. 98281
    Prev
    Next
    INDEX
    Explanations

    either/or programming constructs

    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
    Current
    -0.98
    Angel
    -0.93
     voltou
    -0.90
    ,"
    -0.86
    (.
    -0.86
     Angel
    -0.86
     our
    -0.85
     '_
    -0.85
    urrent
    -0.84
     below
    -0.81
    POSITIVE LOGITS
    ouac
    0.95
     both
    0.91
    pportun
    0.91
    туга
    0.91
     både
    0.90
     Beide
    0.89
     zowel
    0.88
    inama
    0.87
     båda
    0.87
     möj
    0.86
    Activations Density 0.014%

    No Known Activations