© 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. 12070
    Prev
    Next
    INDEX
    Explanations

    Molecular Engineering, Physiology, Nanotechnology

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

    names or abbreviations of scientific disciplines and academic terms.

    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
     eventually
    -0.84
    чин
    -0.81
     Eventually
    -0.78
    eventually
    -0.76
     erfol
    -0.76
    unzip
    -0.75
    ïse
    -0.75
     Jego
    -0.74
    bidities
    -0.73
    σια
    -0.72
    POSITIVE LOGITS
    ⇅
    0.82
     $)$
    0.80
     étui
    0.77
    プル
    0.76
    вла
    0.75
    enares
    0.75
     Scandal
    0.74
     定制
    0.73
    ૯
    0.73
     nguy
    0.72
    Activations Density 0.016%

    No Known Activations