© 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. 124068
    Prev
    Next
    INDEX
    Explanations

    archaeological discoveries and sites

    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
     It
    -2.81
     With
    -2.81
     When
    -2.50
    opheles
    -2.42
    Here
    -2.42
    ։
    -2.41
     Didn
    -2.39
    ?"
    -2.38
     莉
    -2.36
    This
    -2.28
    POSITIVE LOGITS
     イラストレーション
    2.66
    ↵
    2.39
     mauva
    2.33
    诓
    2.30
     エロ
    2.28
    涐
    2.28
     szczeg
    2.27
     роско
    2.25
     ストライプ
    2.23
    暑い
    2.22
    Activations Density 0.003%

    No Known Activations