© 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. 22-GEMMASCOPE-RES-131K
    4. 75158
    Prev
    Next
    INDEX
    Explanations

    gene cloning, field of

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

    file paths in technical or programming text content.

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

    This neuron primarily detects numeric tokens (digit sequences), such as directory or file version numbers and years.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     any
    -1.63
     their
    -1.51
     does
    -1.36
     when
    -1.36
     in
    -1.34
     supremely
    -1.32
     its
    -1.29
     not
    -1.27
     providing
    -1.26
     eight
    -1.23
    POSITIVE LOGITS
     dilapidated
    1.31
     .......
    1.28
     wacky
    1.26
     ADDITIONAL
    1.22
     aufgeführt
    1.22
     colossal
    1.22
     relentless
    1.22
     ........
    1.20
     .........
    1.20
     opulent
    1.20
    Activations Density 0.000%

    No Known Activations