© 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. 48527
    Prev
    Next
    INDEX
    Explanations

    based + material or type

    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
     its
    -2.00
     their
    -1.84
     as
    -1.79
     how
    -1.76
     at
    -1.76
     in
    -1.70
     have
    -1.70
     all
    -1.61
    </b>
    -1.58
    )
    -1.57
    POSITIVE LOGITS
     två
    1.58
    .}~\
    1.54
     véritables
    1.52
    CHARLES
    1.50
     作り方
    1.47
    Etape
    1.47
    ☆☆☆☆
    1.46
    辚
    1.45
    ☆☆☆
    1.43
     constater
    1.42
    Activations Density 0.114%

    No Known Activations