© 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. 813
    Prev
    Next
    INDEX
    Explanations

    statistical learning or physics

    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
     What
    -1.43
     How
    -1.34
     staunch
    -1.34
     disgruntled
    -1.31
     devout
    -1.31
     Of
    -1.30
     Fünf
    -1.29
    riedenheit
    -1.26
     what
    -1.25
     how
    -1.25
    POSITIVE LOGITS
    </
    1.48
    Dieses
    1.45
    </u>
    1.41
    rgb
    1.38
    ”;
    1.34
    うつ
    1.33
    research
    1.31
    ك
    1.31
     renom
    1.29
    ́ng
    1.28
    Activations Density 0.018%

    No Known Activations