© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13287
    Prev
    Next
    INDEX
    Explanations

    on or with applicable

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

    The neuron is highly sensitive to technical identifiers—things like version numbers, uppercase acronyms, CamelCase names, file‐path components, and other code/documentation tokens.

    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
    pores
    -0.88
     meilleurs
    -0.85
    /.../
    -0.85
    lioni
    -0.85
    reas
    -0.84
     aussit
    -0.84
    ;?
    -0.84
     inggris
    -0.83
    hamed
    -0.81
    shank
    -0.81
    POSITIVE LOGITS
     business
    1.05
     businesses
    1.05
     template
    1.05
     templates
    1.02
     planning
    0.94
     like
    0.89
     setups
    0.88
     Pingback
    0.87
     enterprises
    0.86
     requirements
    0.85
    Activations Density 0.077%

    No Known Activations