© 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. 34-GEMMASCOPE-RES-131K
    4. 83972
    Prev
    Next
    INDEX
    Explanations

    yielding or giving in

    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_34/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
    oncesto
    -0.79
    ongoose
    -0.75
     skepticism
    -0.73
    ilot
    -0.72
     skeptical
    -0.70
     aidé
    -0.69
    stí
    -0.69
     distrust
    -0.69
    وتی
    -0.69
     szko
    -0.67
    POSITIVE LOGITS
     succumb
    3.38
     succumbed
    3.20
     cave
    2.75
     capit
    2.70
     bowing
    2.45
     caves
    2.30
     bow
    2.19
     succ
    2.14
     bowed
    2.05
     bows
    2.03
    Activations Density 0.054%

    No Known Activations