© 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. 86782
    Prev
    Next
    INDEX
    Explanations

    starts with N

    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
     four
    -0.94
    を
    -0.92
    つまり
    -0.91
     HUGE
    -0.91
     had
    -0.90
     at
    -0.87
    境界
    -0.86
    를
    -0.86
    と
    -0.85
     three
    -0.84
    POSITIVE LOGITS
    olge
    1.06
     embaraz
    1.04
    のではなく
    1.01
    の情報
    1.00
     trajets
    0.98
    のイメージ
    0.98
    constructed
    0.96
    向けの
    0.96
     york
    0.95
    isant
    0.94
    Activations Density 0.117%

    No Known Activations