© 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. 81152
    Prev
    Next
    INDEX
    Explanations

    configuration options

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

    The neuron fires on command‐line and build‐configuration tokens—especially hyphenated flags and related code/option names.

    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
    ambiguation
    -0.75
     condividere
    -0.75
    productivity
    -0.75
    uali
    -0.74
    沟通
    -0.73
    uktion
    -0.73
     vezes
    -0.73
    Inde
    -0.72
    arnos
    -0.72
     Bist
    -0.71
    POSITIVE LOGITS
    enable
    0.84
    vinas
    0.75
    uties
    0.73
    cob
    0.73
     Monmouth
    0.73
    mites
    0.73
     Approximate
    0.72
    WRP
    0.71
     Dread
    0.71
     Nk
    0.71
    Activations Density 0.010%

    No Known Activations