© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 29166
    Prev
    Next
    INDEX
    Explanations

    Australian rules football

    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
    彼の
    -1.17
    ねえ
    -1.14
     recoge
    -1.13
     朝食
    -1.11
    あとは
    -1.10
    ねー
    -1.10
    私には
    -1.09
    何度も
    -1.08
    rican
    -1.08
    最初は
    -1.06
    POSITIVE LOGITS
     may
    1.23
     will
    1.20
    étique
    1.18
     might
    1.13
     could
    1.10
     all
    1.08
     any
    1.08
    ⻄
    1.04
    orsk
    1.02
    ليد
    1.02
    Activations Density 0.021%

    No Known Activations