© 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. 66874
    Prev
    Next
    INDEX
    Explanations

    code structures and declarations

    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
    𝐅
    -1.53
     этой
    -1.51
     last
    -1.48
    空调
    -1.47
    </em>
    -1.46
    ...
    -1.44
    </h3>
    -1.41
    ”
    -1.33
     их
    -1.32
    甚至
    -1.32
    POSITIVE LOGITS
     but
    1.84
     tiada
    1.69
     Одна
    1.63
     although
    1.62
     Однако
    1.61
     Although
    1.59
    肄
    1.55
     However
    1.55
     consideró
    1.55
    诧
    1.54
    Activations Density 0.002%

    No Known Activations