© 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. 22-GEMMASCOPE-RES-131K
    7. 66315
    Prev
    Next
    INDEX
    Explanations

    sentence start

    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_22/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
     ondu
    -1.16
     Coutinho
    -1.07
    づくり
    -1.07
    corrhi
    -1.07
     ‘’
    -1.06
    pleasant
    -1.04
    Ná
    -1.02
    vermectin
    -1.02
    cking
    -1.02
     dieu
    -1.02
    POSITIVE LOGITS
     also
    1.07
     use
    1.06
     as
    1.05
     only
    1.04
    ～！
    1.02
    8
    1.01
     integrate
    0.99
    ～。
    0.98
     including
    0.97
     is
    0.95
    Activations Density 0.014%

    No Known Activations