© 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. 10-GEMMASCOPE-RES-131K
    7. 1683
    Prev
    Next
    INDEX
    Explanations

    specific code syntax delimiters

    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_10/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
    Tetapi
    -2.34
    ).
    -2.22
    Demikian
    -2.16
    ronesia
    -2.11
    ſelves
    -2.06
    ۴
    -2.03
    ୩
    -2.03
    ۸
    -2.03
    Lebih
    -2.02
    Both
    -2.00
    POSITIVE LOGITS
     to
    2.16
    "
    1.85
    t
    1.76
    龵
    1.66
    er
    1.66
     
    1.65
    0
    1.64
     say
    1.59
     escuchado
    1.59
     vrijdag
    1.51
    Activations Density 0.006%

    No Known Activations