© 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. 54166
    Prev
    Next
    INDEX
    Explanations

    steps or second items

    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
    -1.47
    <eos>
    -1.41
    最后
    -1.36
     наконец
    -1.33
     infine
    -1.26
     cuối
    -1.21
     finally
    -1.20
     Finally
    -1.20
     Lastly
    -1.17
    final
    -1.16
    POSITIVE LOGITS
     secondly
    1.66
    Secondly
    1.55
    其次
    1.54
     Secondly
    1.52
    次に
    1.43
     second
    1.34
    続いて
    1.18
     نداره
    1.09
    second
    1.08
     教程
    1.06
    Activations Density 0.023%

    No Known Activations