© 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. 12478
    Prev
    Next
    INDEX
    Explanations

    English honorifics and titles

    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
     to
    -1.20
     dadurch
    -1.12
     susceptible
    -0.94
     assailants
    -0.93
    les
    -0.93
     структуры
    -0.92
     niezbęd
    -0.92
     sufficient
    -0.91
     personenbez
    -0.91
    ie
    -0.90
    POSITIVE LOGITS
     étui
    1.06
     importants
    1.05
    moderne
    1.02
     sintético
    1.02
    kkende
    1.02
    nss
    1.00
    眉头
    0.98
    ındaki
    0.98
     rústico
    0.98
    なんか
    0.97
    Activations Density 0.096%

    No Known Activations