© 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. 95433
    Prev
    Next
    INDEX
    Explanations

    programming code closing punctuation

    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
    -1.12
     at
    -1.01
     Администра
    -0.90
    hecimento
    -0.90
     сбор
    -0.88
     other
    -0.87
     of
    -0.87
     and
    -0.87
     if
    -0.87
     ie
    -0.86
    POSITIVE LOGITS
    ilí
    1.12
     Fakta
    1.09
     Aler
    1.08
     pases
    1.03
     fó
    1.03
    íra
    1.03
     infal
    1.02
     bombas
    1.01
     aspi
    1.00
    エンジ
    0.98
    Activations Density 0.004%

    No Known Activations