© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48768
    Prev
    Next
    INDEX
    Explanations

    two different entities

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

    The neuron reliably detects the word “two.”

    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
    了一個
    -1.64
    着一个
    -1.51
    了一个
    -1.46
    %，
    -1.41
    yship
    -1.35
     numerous
    -1.32
    蛧
    -1.31
     various
    -1.30
     beberapa
    -1.29
    了许多
    -1.28
    POSITIVE LOGITS
     of
    2.38
     sets
    2.13
     separate
    2.09
     different
    2.06
     kinds
    1.92
     distinct
    1.69
     dozen
    1.63
     seperate
    1.63
     pieces
    1.60
     types
    1.56
    Activations Density 0.128%

    No Known Activations