© 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. 22-GEMMASCOPE-RES-131K
    4. 9595
    Prev
    Next
    INDEX
    Explanations

    original parts and configurations

    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_22/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
    íferos
    -1.23
    BIÉN
    -1.20
     različ
    -1.16
    alui
    -1.16
    lutning
    -1.15
    嚕
    -1.15
    楼梯
    -1.14
    櫂
    -1.12
     السياس
    -1.11
    icznego
    -1.08
    POSITIVE LOGITS
     original
    1.53
     existing
    1.47
     still
    1.40
    เดิม
    1.39
     default
    1.22
    original
    1.20
     oryginal
    1.17
     originali
    1.17
     that
    1.14
     your
    1.13
    Activations Density 0.020%

    No Known Activations