© 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. 85041
    Prev
    Next
    INDEX
    Explanations

    at least

    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
     would
    -1.46
    1
    -1.39
     are
    -1.26
     wraz
    -1.24
    brania
    -1.20
     decided
    -1.18
     grop
    -1.17
    这些
    -1.16
     for
    -1.16
    </em>
    -1.16
    POSITIVE LOGITS
    齶
    1.53
    给我们
    1.52
     наших
    1.52
     любой
    1.42
     современной
    1.41
     我们
    1.40
    又要
    1.37
     quente
    1.37
     современных
    1.37
    both
    1.34
    Activations Density 0.034%

    No Known Activations