© 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. 60564
    Prev
    Next
    INDEX
    Explanations

    Cypress Park, Interleukin, Q:, 20

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

    empty line breaks or whitespace between paragraphs.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron never activates on any token—it doesn’t detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     tailored
    -1.39
     what
    -1.36
     ostensibly
    -1.33
     one
    -1.32
     there
    -1.31
     highlighted
    -1.30
     seemingly
    -1.29
     every
    -1.29
     with
    -1.27
     even
    -1.26
    POSITIVE LOGITS
     อย
    1.23
     dreary
    1.21
     Estructura
    1.19
     opulent
    1.19
     elegantly
    1.19
     dismal
    1.19
     magnific
    1.18
     delightfully
    1.16
     amd
    1.15
     colossal
    1.15
    Activations Density 0.000%

    No Known Activations