© 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. 42417
    Prev
    Next
    INDEX
    Explanations

    between locations or numbers

    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
    𓐍
    -3.31
     overarching
    -3.23
    や
    -3.20
    餮
    -3.05
    หรือ
    -2.84
     
    -2.78
    </b>
    -2.75
    ”
    -2.64
    萏
    -2.63
     seine
    -2.58
    POSITIVE LOGITS
     Then
    3.33
    ابراین
    2.77
    pecabe
    2.66
     видит
    2.64
     увидел
    2.64
    也将
    2.56
     However
    2.50
     haughty
    2.48
     municipales
    2.47
    岽
    2.47
    Activations Density 0.063%

    No Known Activations