© 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. 70899
    Prev
    Next
    INDEX
    Explanations

    's followed by ordinal or superlative

    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
     that
    -1.45
     fatale
    -1.43
     lakini
    -1.41
    🙅
    -1.40
     الآخر
    -1.40
     RSITY
    -1.40
     第三
    -1.38
     dobu
    -1.36
     недавно
    -1.36
    👅
    -1.34
    POSITIVE LOGITS
    </h2>
    2.22
     a
    1.95
     only
    1.85
    </h1>
    1.74
     '
    1.59
     most
    1.59
     best
    1.56
    </h3>
    1.52
     "
    1.52
     sério
    1.51
    Activations Density 0.068%

    No Known Activations