© 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. 84434
    Prev
    Next
    INDEX
    Explanations

    Karma, intuition, de-stress

    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
    -1.91
    וּ
    -1.91
    ֶּ
    -1.70
    ַּ
    -1.53
     then
    -1.52
    ֵּ
    -1.48
    ִּ
    -1.45
    וֹ
    -1.30
    ְר
    -1.28
    駅から
    -1.27
    POSITIVE LOGITS
     your
    1.68
    ׇ
    1.66
     you
    1.50
     kathol
    1.34
     holdt
    1.28
     сахара
    1.24
     ܕ
    1.23
     Pfar
    1.23
     particularly
    1.22
     ܐ
    1.20
    Activations Density 0.006%

    No Known Activations