© 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. 53789
    Prev
    Next
    INDEX
    Explanations

    waste material and ethyl alcohol

    np_acts-logits-general · gemini-2.5-flash-lite

    open-source software license text and copyright notices in code files.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     ولك
    -0.65
     granat
    -0.64
    TextFormField
    -0.63
     have
    -0.63
     arşivlendi
    -0.63
    แข็ง
    -0.62
     锁
    -0.62
    月光
    -0.61
    EINVAL
    -0.60
     зам
    -0.60
    POSITIVE LOGITS
    issimi
    0.78
    outi
    0.75
     uitz
    0.71
    lanie
    0.68
    pgp
    0.68
    pondi
    0.68
     Melee
    0.67
     Param
    0.67
    tonic
    0.67
    ulia
    0.66
    Activations Density 0.060%

    No Known Activations