© 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. 85360
    Prev
    Next
    INDEX
    Explanations

    unclear

    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
    );?>
    -1.65
    ㈠
    -1.38
    ológicas
    -1.34
     miejscu
    -1.34
    ناعة
    -1.34
     tends
    -1.30
    Ārējās
    -1.29
     ruthless
    -1.26
     restrict
    -1.26
    湄
    -1.25
    POSITIVE LOGITS
    是怎么回事
    1.46
     المحت
    1.32
    rehensible
    1.30
     tages
    1.30
     kuid
    1.29
     kut
    1.29
     sadar
    1.28
    慚
    1.25
     hain
    1.24
    지는
    1.23
    Activations Density 0.016%

    No Known Activations