© 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. 105078
    Prev
    Next
    INDEX
    Explanations

    special characters and accents

    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
    瑨
    -2.72
    襌
    -2.56
    ſſer
    -2.53
     começ
    -2.44
    🛇
    -2.44
    庒
    -2.42
    灕
    -2.41
    屨
    -2.38
    馘
    -2.34
     dubbed
    -2.33
    POSITIVE LOGITS
    ’
    2.61
     nieco
    2.30
     tens
    2.20
     waning
    2.19
    are
    2.13
     sporadic
    2.11
     undeveloped
    2.09
     fake
    2.08
     shove
    2.08
    釭
    2.06
    Activations Density 0.000%

    No Known Activations