© 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. 40672
    Prev
    Next
    INDEX
    Explanations

    introducing alternatives

    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
     этими
    -1.38
     these
    -1.36
    </em>
    -1.32
    และ
    -1.31
    </u>
    -1.28
    ↵↵
    -1.28
     dificultades
    -1.27
    </h4>
    -1.27
    </strong>
    -1.25
     wszystkich
    -1.25
    POSITIVE LOGITS
     because
    1.33
    énération
    1.22
    tillery
    1.13
    POSAL
    1.13
    іль
    1.12
     '@/
    1.10
     =="
    1.10
     if
    1.09
    етки
    1.09
    קש
    1.09
    Activations Density 0.021%

    No Known Activations