© 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. 71474
    Prev
    Next
    INDEX
    Explanations

    physical touch and affection

    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
     for
    -1.05
     Tugend
    -1.00
     set
    -0.98
     zusätzlich
    -0.94
     it
    -0.93
    w
    -0.93
    mix
    -0.93
    zzino
    -0.91
     где
    -0.91
     Flexib
    -0.90
    POSITIVE LOGITS
     cukru
    1.26
     různých
    1.20
     различни
    1.17
     apret
    1.16
     chyb
    1.14
     manqué
    1.14
    Vlast
    1.13
    Çok
    1.12
    Inne
    1.12
     algodón
    1.10
    Activations Density 0.040%

    No Known Activations