© 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. 22-GEMMASCOPE-RES-131K
    7. 66798
    Prev
    Next
    INDEX
    Explanations

    accessing list elements

    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_22/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
     and
    -1.28
    iseks
    -0.97
     is
    -0.94
    骉
    -0.93
    mær
    -0.91
    ÄR
    -0.89
    navigationBar
    -0.88
     ampere
    -0.88
    леб
    -0.87
    ztes
    -0.87
    POSITIVE LOGITS
     one
    1.28
    𝚘
    1.13
    ()[
    0.93
     worst
    0.93
     chacune
    0.91
    風險
    0.91
     egyik
    0.90
    蒐
    0.90
    quele
    0.88
    kedés
    0.88
    Activations Density 0.007%

    No Known Activations