© 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. 58573
    Prev
    Next
    INDEX
    Explanations

    iterator

    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
    섹
    -0.75
    Julius
    -0.72
     township
    -0.66
    🔽
    -0.66
     Wikisource
    -0.66
    öhnen
    -0.66
     stazione
    -0.66
     völ
    -0.65
     dott
    -0.65
     Kraft
    -0.65
    POSITIVE LOGITS
     iterator
    4.56
    Iterator
    4.47
     Iterator
    4.22
     iter
    4.09
    iterator
    3.97
    iter
    3.61
    Iter
    3.45
     Iter
    3.30
    迭代
    3.20
    ITER
    3.09
    Activations Density 0.108%

    No Known Activations