© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42318
    Prev
    Next
    INDEX
    Explanations

    the process of rotating or heating

    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
     including
    -1.89
     even
    -1.87
     all
    -1.68
     its
    -1.62
     this
    -1.62
     still
    -1.61
     despite
    -1.54
     see
    -1.52
     over
    -1.46
     more
    -1.42
    POSITIVE LOGITS
    Otro
    1.40
     ſub
    1.40
     peindre
    1.38
     raconter
    1.30
    سكرية
    1.30
    acje
    1.29
    called
    1.28
    慙
    1.28
    مشخص
    1.28
    ofern
    1.27
    Activations Density 0.841%

    No Known Activations