© 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. 10-GEMMASCOPE-RES-131K
    7. 8290
    Prev
    Next
    INDEX
    Explanations

    ingredient

    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
    e
    -3.31
    or
    -3.27
    u
    -3.03
    an
    -2.77
    as
    -2.61
    =
    -2.27
    臯
    -2.22
    孩子
    -2.19
    </b>
    -2.17
    i
    -2.13
    POSITIVE LOGITS
     綠
    2.61
     兒童
    2.56
    medriver
    2.38
    
    2.31
    OUTUBE
    2.31
    を行い
    2.28
     壓
    2.27
    猹
    2.23
     兩
    2.17
     AQUI
    2.17
    Activations Density 0.002%

    No Known Activations