© 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. 38911
    Prev
    Next
    INDEX
    Explanations

    military ranks

    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
    饜
    -1.64
     latine
    -1.49
     chiesa
    -1.43
     commencé
    -1.43
     Apakah
    -1.42
     décidé
    -1.41
     recensione
    -1.40
     ricetta
    -1.39
    其他
    -1.38
     proposés
    -1.38
    POSITIVE LOGITS
    ),
    1.81
     who
    1.71
     at
    1.43
    趼
    1.41
     couldn
    1.38
     in
    1.38
    Jungkook
    1.34
     \
    1.33
     have
    1.30
    鋮
    1.27
    Activations Density 0.018%

    No Known Activations