© 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. 102897
    Prev
    Next
    INDEX
    Explanations

    programming code separators

    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
     Spoilers
    -0.88
    県の
    -0.83
    lijke
    -0.77
    MATT
    -0.73
    SECUR
    -0.73
    UGGEST
    -0.72
    듭
    -0.72
    IMDB
    -0.72
     uterine
    -0.71
    ର
    -0.71
    POSITIVE LOGITS
     Button
    1.04
    Button
    1.02
     soprattutto
    0.93
    ipi
    0.79
     Body
    0.77
    знать
    0.77
     Statement
    0.76
    𝔹
    0.76
    estival
    0.75
     Label
    0.73
    Activations Density 0.073%

    No Known Activations