© 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. 35758
    Prev
    Next
    INDEX
    Explanations

    definition of terms

    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
     jesu
    -1.09
     ikon
    -1.07
     fön
    -1.02
     batas
    -1.01
     parfüm
    -1.00
     komfor
    -0.98
     berät
    -0.98
     konfig
    -0.97
     alfab
    -0.96
     jaja
    -0.96
    POSITIVE LOGITS
     довольно
    1.06
     charité
    1.06
    主力
    1.06
    旋律
    1.02
    Mitarbeiter
    1.00
    使用
    1.00
     menggunakan
    0.99
     есть
    0.99
     męska
    0.98
    ghted
    0.98
    Activations Density 0.007%

    No Known Activations