© 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. 70830
    Prev
    Next
    INDEX
    Explanations

    pronoun / title followed by noun

    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
     like
    -2.08
     this
    -1.76
     (
    -1.70
     or
    -1.70
     H
    -1.66
     J
    -1.63
     all
    -1.63
     even
    -1.63
    like
    -1.59
     now
    -1.58
    POSITIVE LOGITS
     verhind
    2.19
     verborgen
    1.75
     konkret
    1.63
     paie
    1.57
     verbind
    1.55
     nimmer
    1.54
     heilig
    1.53
    罍
    1.53
     acht
    1.50
     bestem
    1.49
    Activations Density 0.073%

    No Known Activations