© 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. 113122
    Prev
    Next
    INDEX
    Explanations

    number values

    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
    some
    -1.40
     so
    -1.24
    #%%
    -1.20
     می‌ده
    -1.13
    <tr>
    -1.12
    slf
    -1.09
    ximos
    -1.08
    /***
    -1.07
    ільки
    -1.06
    ug
    -1.05
    POSITIVE LOGITS
    ਗ਼
    1.42
    ਫ਼
    1.40
    tatuaje
    1.32
    ਖ਼
    1.26
    pendentif
    1.21
     that
    1.19
    אתה
    1.19
    辂
    1.16
    sätzlich
    1.16
    laundry
    1.16
    Activations Density 0.162%

    No Known Activations