© 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. 6749
    Prev
    Next
    INDEX
    Explanations

    free software

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

    The neuron is keyed to boilerplate “metadata” tokens—things like all-caps service names (e.g. WIRE), timestamps, numeric codes, section labels, etc.

    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
    事前に
    -0.69
     repr
    -0.69
     subsequ
    -0.67
     APT
    -0.67
     Direc
    -0.66
     UNICEF
    -0.66
     Whal
    -0.65
    fils
    -0.64
     دهنده
    -0.63
     湯
    -0.63
    POSITIVE LOGITS
     Magnus
    0.73
     waktu
    0.69
    Magnus
    0.67
    ensburg
    0.66
     Kil
    0.65
    osity
    0.65
     Rams
    0.64
    لالة
    0.64
    sun
    0.64
     hubs
    0.64
    Activations Density 0.073%

    No Known Activations