© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103656
    Prev
    Next
    INDEX
    Explanations

    file extensions

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

    file extensions in file paths and filenames.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on file‐ and path‐name tokens (base names, extensions, and related segments).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </b>
    -1.66
    вшим
    -1.49
     THOSE
    -1.48
     sufic
    -1.45
     dè
    -1.43
    those
    -1.38
     rè
    -1.36
    crates
    -1.35
     chè
    -1.33
     cantando
    -1.32
    POSITIVE LOGITS
     usually
    1.62
     that
    1.58
     until
    1.44
    曩
    1.42
     или
    1.42
     Seems
    1.42
     beside
    1.38
     about
    1.36
     on
    1.32
     while
    1.26
    Activations Density 0.093%

    No Known Activations