© 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. 99687
    Prev
    Next
    INDEX
    Explanations

    within or between

    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
    </h3>
    -1.39
    っとり
    -1.38
    compati
    -1.32
     those
    -1.31
    っぱり
    -1.30
    脔
    -1.26
     它
    -1.23
     ᾿
    -1.23
     افرادی
    -1.23
    mitteilung
    -1.20
    POSITIVE LOGITS
     between
    1.70
    一旦
    1.30
     بدون
    1.26
     dalam
    1.24
     penso
    1.22
     dengan
    1.21
     back
    1.20
     my
    1.19
     through
    1.17
    早期
    1.17
    Activations Density 0.010%

    No Known Activations