© 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. 22-GEMMASCOPE-RES-131K
    7. 67014
    Prev
    Next
    INDEX
    Explanations

    Wilson Farm LLC

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

    This neuron did not activate on any tokens in these excerpts, indicating it does not respond to any of the presented text patterns.

    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
     before
    -1.47
     with
    -1.39
     usually
    -1.36
     mostly
    -1.27
     just
    -1.24
     for
    -1.23
     ostensibly
    -1.23
     several
    -1.22
     using
    -1.21
     until
    -1.21
    POSITIVE LOGITS
    
    1.26
     extravag
    1.24
     SPECIFIC
    1.21
     astounding
    1.20
    athered
    1.19
     PARTICULAR
    1.18
     SEPAR
    1.16
    ਗ਼
    1.16
     GETTING
    1.16
    oped
    1.16
    Activations Density 0.000%

    No Known Activations