© 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. 24024
    Prev
    Next
    INDEX
    Explanations

    code comments and setup

    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
     melap
    -1.51
    ＠
    -1.31
    ínio
    -1.31
    Even
    -1.30
     bahkan
    -1.28
    you
    -1.27
    orrhea
    -1.27
     even
    -1.27
     bawah
    -1.23
    Bahkan
    -1.23
    POSITIVE LOGITS
     confirmed
    1.41
     것을
    1.35
     repens
    1.34
     kém
    1.32
     debería
    1.31
     stylu
    1.28
    embl
    1.24
     proposed
    1.23
     tidak
    1.22
    スン
    1.22
    Activations Density 0.004%

    No Known Activations