© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49148
    Prev
    Next
    INDEX
    Explanations

    Installer::, products/, real>, structure)

    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
    <0xDA>
    -0.81
    playerName
    -0.78
    tingen
    -0.75
    ሁ
    -0.71
    stationary
    -0.71
     Helle
    -0.71
    ysy
    -0.67
     contacts
    -0.66
    FieldBuilder
    -0.66
     planner
    -0.65
    POSITIVE LOGITS
    נט
    0.71
    Search
    0.67
    得点
    0.66
    grass
    0.63
    mid
    0.62
    Id
    0.62
    base
    0.61
     sikkert
    0.61
     segurança
    0.61
    Е
    0.61
    Activations Density 0.048%

    No Known Activations