© 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. 14283
    Prev
    Next
    INDEX
    Explanations

    in a place or state

    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
    rfan
    -1.53
    为什么会
    -1.50
     increasingly
    -1.44
    transporte
    -1.38
    &
    -1.38
     causando
    -1.37
    哪儿
    -1.36
    ՚
    -1.36
     probable
    -1.34
    告诉我
    -1.34
    POSITIVE LOGITS
     able
    1.67
    </strong>
    1.61
     содержание
    1.58
    屹
    1.57
     می‌گوید
    1.53
    </sub>
    1.52
    던
    1.46
    та
    1.45
     originally
    1.43
     как
    1.40
    Activations Density 0.030%

    No Known Activations