© 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. 58727
    Prev
    Next
    INDEX
    Explanations

    as well as

    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
     vienas
    -1.15
     will
    -1.13
     your
    -1.09
     each
    -1.07
     metav
    -1.05
    硖
    -1.05
     every
    -1.03
     như
    -1.03
     sufficient
    -1.02
    壜
    -1.02
    POSITIVE LOGITS
    几种
    1.23
    </h4>
    1.20
    說道
    1.17
     traditionnelle
    1.13
    三种
    1.12
    多种
    1.12
    dians
    1.12
    ੍ਹ
    1.10
     چیز
    1.09
     グ
    1.09
    Activations Density 0.027%

    No Known Activations