© 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. 22-GEMMASCOPE-RES-131K
    7. 67525
    Prev
    Next
    INDEX
    Explanations

    I wanted to create

    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
    ּוֹ
    -1.88
    ֶּ
    -1.40
    ִּ
    -1.39
    ְּ
    -1.29
     السياس
    -1.24
    ֵּ
    -1.19
    ַּ
    -1.17
     الحكومة
    -1.16
    ggable
    -1.13
    וּ
    -1.08
    POSITIVE LOGITS
     idea
    1.71
     ideas
    1.54
     wanted
    1.42
     concept
    1.33
     I
    1.28
     inspired
    1.20
     inspiration
    1.20
     originally
    1.14
    イメージ
    1.12
     thought
    1.10
    Activations Density 0.040%

    No Known Activations