© 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. 1673
    Prev
    Next
    INDEX
    Explanations

    DES, Abd, Erwin, Thunderbolt

    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
     femininas
    -3.02
    these
    -2.88
    圌
    -2.88
    ⚣
    -2.88
    enablog
    -2.83
    釭
    -2.78
    鋮
    -2.77
    ⬈
    -2.69
    鹩
    -2.59
     queridos
    -2.58
    POSITIVE LOGITS
    *
    3.56
    1
    3.38
    ↵↵
    3.11
    \
    3.11
    n
    3.08
    <i>
    3.05
     -
    2.98
    ma
    2.92
    <b>
    2.86
    –
    2.72
    Activations Density 0.035%

    No Known Activations