© 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. 58819
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
    <em>
    -2.58
    ↵↵
    -2.52
    .”
    -2.39
    </sub>
    -2.36
     anderes
    -2.16
     zentralen
    -2.16
    </strong>
    -2.16
    </h3>
    -2.13
     französ
    -2.09
    érales
    -2.09
    POSITIVE LOGITS
    '
    2.45
    ﺐ
    2.28
     kemudian
    2.27
     diza
    2.02
    1
    1.91
    навли
    1.86
     مانند
    1.80
     رت
    1.80
     短发
    1.80
     and
    1.80
    Activations Density 0.089%

    No Known Activations