© 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. 75479
    Prev
    Next
    INDEX
    Explanations

    these accomplishments

    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
     futuras
    -1.11
     futuros
    -1.03
    $,
    -0.98
    engkapnya
    -0.93
     if
    -0.92
     床
    -0.92
    всегда
    -0.88
     quello
    -0.88
    radan
    -0.88
     ofrecemos
    -0.86
    POSITIVE LOGITS
     these
    5.69
     estos
    3.80
    these
    3.72
    这些
    3.63
     этих
    3.39
    這些
    3.25
    These
    3.17
     эти
    3.11
     These
    3.09
    这两
    2.83
    Activations Density 0.060%

    No Known Activations