© 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. 34-GEMMASCOPE-RES-131K
    7. 2163
    Prev
    Next
    INDEX
    Explanations

    Russell followed by names

    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
     publicité
    -0.89
    挾
    -0.86
     CULTURAL
    -0.86
     следующем
    -0.85
     высокая
    -0.85
     Righteous
    -0.84
     Tenga
    -0.84
    鉑
    -0.83
    將軍
    -0.83
     Finances
    -0.82
    POSITIVE LOGITS
     Square
    0.92
    冈
    0.90
     Запад
    0.90
     kemudian
    0.89
    혁
    0.86
     хотя
    0.85
    mania
    0.85
    unique
    0.84
     Manuscript
    0.84
    bildschirm
    0.84
    Activations Density 0.004%

    No Known Activations