© 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. 95468
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    ちゃんは
    -1.37
    ちゃんが
    -1.35
    ちゃんの
    -1.35
     trám
    -1.32
    ästi
    -1.23
    ኗ
    -1.18
    の詳細
    -1.13
    Estou
    -1.12
    在我们
    -1.12
    懨
    -1.09
    POSITIVE LOGITS
     when
    1.09
     while
    1.02
     latter
    0.97
    但却
    0.95
     connotation
    0.93
     after
    0.92
    支店
    0.91
     Throughout
    0.91
     Where
    0.90
     ursprünglich
    0.88
    Activations Density 0.128%

    No Known Activations