© 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. 128998
    Prev
    Next
    INDEX
    Explanations

    ninth circuit

    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
     hebben
    -2.59
     представителей
    -2.44
     hanem
    -2.44
     έχουν
    -2.41
    ارتمان
    -2.28
     I
    -2.27
     hermana
    -2.25
     маленьких
    -2.25
     otras
    -2.23
     sicheren
    -2.20
    POSITIVE LOGITS
    蜮
    3.17
    趼
    2.66
    ний
    2.41
    }$
    2.28
    皤
    2.23
     概念
    2.20
    Edy
    2.19
     tain
    2.16
    嵎
    2.16
    ؟
    2.14
    Activations Density 0.017%

    No Known Activations