© 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. 34-GEMMASCOPE-RES-131K
    7. 84692
    Prev
    Next
    INDEX
    Explanations

    user permissions and inputs

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

    The neuron fires on code identifiers and type/field names written in TitleCase or ALL_CAPS (i.e. capitalized tokens in code).

    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
    argate
    -0.74
    偷偷
    -0.73
    peth
    -0.73
     MODERN
    -0.72
    vistar
    -0.72
     Headers
    -0.71
     сайте
    -0.71
     Lilian
    -0.70
    elite
    -0.70
     건
    -0.69
    POSITIVE LOGITS
    Connection
    1.05
     Connection
    0.94
     input
    0.87
    input
    0.86
    ículos
    0.86
     mutation
    0.85
    mutation
    0.84
     inputs
    0.82
    Input
    0.81
    payload
    0.81
    Activations Density 0.006%

    No Known Activations