© 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. 34-GEMMASCOPE-RES-131K
    7. 33847
    Prev
    Next
    INDEX
    Explanations

    keywords, questions, declarations

    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
     by
    -0.92
    ！　
    -0.84
     sucht
    -0.83
    스템
    -0.82
     個
    -0.82
    瀟
    -0.80
     upfront
    -0.79
     Altstadt
    -0.78
     ander
    -0.78
     with
    -0.76
    POSITIVE LOGITS
    |.
    1.06
    |
    0.96
    attempts
    0.93
    ﺳ
    0.90
     astounding
    0.89
     Attempts
    0.86
     gelöst
    0.82
     trám
    0.82
     notamment
    0.81
    ihnachten
    0.81
    Activations Density 0.000%

    No Known Activations