© 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. 2417
    Prev
    Next
    INDEX
    Explanations

    sql date conversion

    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
     sayin
    -0.72
    ipc
    -0.63
     れ
    -0.62
     nutri
    -0.62
    からの
    -0.61
     legs
    -0.60
     Amar
    -0.58
     ті
    -0.58
    halo
    -0.58
     વ
    -0.58
    POSITIVE LOGITS
     Biggs
    0.74
     terraced
    0.73
     Aprend
    0.73
    czył
    0.71
    itant
    0.71
     plenary
    0.68
    حث
    0.68
     услыша
    0.67
    бражение
    0.66
    贍
    0.66
    Activations Density 0.086%

    No Known Activations