© 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. 4051
    Prev
    Next
    INDEX
    Explanations

    board and board-related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    </h5>
    -1.07
    </td>
    -1.06
    ila
    -1.05
    ists
    -0.97
    ik
    -0.95
     —
    -0.94
    iv
    -0.93
    ps
    -0.92
     кажется
    -0.91
    หรือ
    -0.90
    POSITIVE LOGITS
    Board
    1.47
     board
    1.46
     boards
    1.42
     BOARD
    1.41
    board
    1.39
    getBoard
    1.30
     Board
    1.21
     CHAIRMAN
    1.20
    董事
    1.20
    room
    1.20
    Activations Density 0.022%

    No Known Activations