© 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. 73581
    Prev
    Next
    INDEX
    Explanations

    http and https links

    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
     but
    -1.54
     those
    -1.48
     while
    -1.13
     both
    -1.05
     all
    -1.03
     In
    -1.02
     strange
    -0.99
     Instead
    -0.99
     change
    -0.99
     neben
    -0.98
    POSITIVE LOGITS
     applau
    1.23
     détaillé
    1.20
     dévelo
    1.18
    を買う
    1.13
     erneu
    1.13
     сайта
    1.11
     correctement
    1.09
    わざわざ
    1.09
    どれだけ
    1.09
    だいたい
    1.09
    Activations Density 0.004%

    No Known Activations