© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 9574
    Prev
    Next
    INDEX
    Explanations

    "non-" prefixes

    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
    ᕮ
    -1.75
    が上が
    -1.59
    が
    -1.55
    呟
    -1.55
     帅气
    -1.51
    それにしても
    -1.49
     bén
    -1.48
     kanton
    -1.46
    と
    -1.45
    觊
    -1.45
    POSITIVE LOGITS
    主要的
    1.72
    S
    1.56
     necessarily
    1.50
    D
    1.47
    there
    1.44
    It
    1.44
    Even
    1.42
    影像
    1.41
     even
    1.40
    When
    1.40
    Activations Density 0.025%

    No Known Activations