© 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. 60642
    Prev
    Next
    INDEX
    Explanations

    MIRA EXCEL, software, modulus

    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
    Gib
    -0.83
    Γ
    -0.82
    зом
    -0.71
    achter
    -0.70
     счастли
    -0.69
    pagina
    -0.68
     direta
    -0.67
    anego
    -0.67
     remarqu
    -0.66
     vermelhas
    -0.66
    POSITIVE LOGITS
     budge
    0.76
     pect
    0.71
     kwietnia
    0.69
    曲を
    0.69
    чні
    0.68
     miejsce
    0.68
     軟
    0.68
    Institu
    0.66
    essori
    0.66
     famil
    0.66
    Activations Density 0.034%

    No Known Activations