© 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. 1783
    Prev
    Next
    INDEX
    Explanations

    doi identifiers

    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
     لیگ
    -0.84
    utrition
    -0.84
    ্র
    -0.82
    到位
    -0.77
    茁
    -0.74
    anshi
    -0.73
     литров
    -0.73
    蹤
    -0.72
     turnaround
    -0.71
    itzender
    -0.71
    POSITIVE LOGITS
    org
    1.22
     org
    1.20
    ORG
    0.97
     doi
    0.91
     Org
    0.90
    俺は
    0.90
    Org
    0.87
     MANUAL
    0.81
     ড
    0.80
    ActionButton
    0.79
    Activations Density 0.004%

    No Known Activations