© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92328
    Prev
    Next
    INDEX
    Explanations

    bif, bic, bip words

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

    The neuron is triggered by tokens containing the letter sequence “bif” (e.g. “Bifrost,” “bifurcation,” 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
    ͗
    -0.85
     talkin
    -0.76
    允
    -0.73
    pik
    -0.72
    baya
    -0.71
    yv
    -0.71
    燎
    -0.71
     зло
    -0.70
     ა
    -0.69
    FileInputStream
    -0.69
    POSITIVE LOGITS
     函数
    0.84
    However
    0.84
     Однако
    0.83
    bip
    0.81
     Faso
    0.78
    Proced
    0.75
    наче
    0.74
     However
    0.73
    owiec
    0.73
    straat
    0.73
    Activations Density 0.057%

    No Known Activations