© 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. 58807
    Prev
    Next
    INDEX
    Explanations

    book boards

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

    The neuron flags bibliographic metadata—particularly edition and format details—by spotting numbers, dates, and words like “paperback,” “edition,” “issued,” and “in.”

    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
     consectetur
    -0.81
    SAMPLES
    -0.76
    luk
    -0.74
    ">@
    -0.73
    boll
    -0.72
    WriteHeader
    -0.72
    stopper
    -0.71
     chapeau
    -0.71
     Использу
    -0.71
    coat
    -0.68
    POSITIVE LOGITS
     boards
    3.05
     Boards
    2.39
    boards
    2.31
    Boards
    2.05
     board
    1.91
    board
    1.59
    Board
    1.51
     Board
    1.49
    BOARD
    1.48
     BOARD
    1.39
    Activations Density 0.038%

    No Known Activations