© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111872
    Prev
    Next
    INDEX
    Explanations

    variables u and v

    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
     frisch
    -1.20
    取る
    -1.09
     my
    -1.07
     providing
    -1.07
     you
    -1.07
     during
    -1.05
    Цитата
    -1.05
     zve
    -1.03
     グラム
    -1.02
     Providing
    -1.02
    POSITIVE LOGITS
    "">
    1.41
    </b>
    1.18
     tentang
    1.16
    )}+
    1.16
    这些
    1.16
    也就是
    1.15
     retrouve
    1.15
    ('/:
    1.15
    aggia
    1.13
    はこの
    1.11
    Activations Density 0.017%

    No Known Activations