© 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. 67744
    Prev
    Next
    INDEX
    Explanations

    Adobe software

    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
     seiner
    -1.22
     pirm
    -1.21
     leicht
    -1.16
     ПА
    -1.13
    version
    -1.13
     seguirá
    -1.10
    水晶
    -1.09
     version
    -1.09
    很容易
    -1.08
    ：[
    -1.08
    POSITIVE LOGITS
    </b>
    1.38
    現在は
    1.31
     アウト
    1.25
    ueuse
    1.20
    icoot
    1.19
     allerede
    1.16
    esai
    1.13
     Currently
    1.13
     Traditionally
    1.11
     Photoshop
    1.10
    Activations Density 0.062%

    No Known Activations