© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48623
    Prev
    Next
    INDEX
    Explanations

    types of closed systems

    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
    ҕ
    -0.77
    dimer
    -0.76
     zile
    -0.74
    Dim
    -0.74
    <0xAC>
    -0.73
    delim
    -0.72
     enceinte
    -0.71
    Orlando
    -0.71
     Ains
    -0.70
     Rapid
    -0.70
    POSITIVE LOGITS
     sağ
    0.90
    ft
    0.75
     \\
    0.73
    负责
    0.72
     چنین
    0.70
    SetPosition
    0.69
     vorigen
    0.69
     Allein
    0.69
    进行
    0.68
    任意
    0.68
    Activations Density 0.017%

    No Known Activations