© 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. 10-GEMMASCOPE-RES-131K
    7. 11420
    Prev
    Next
    INDEX
    Explanations

    sufficient quantity or quality

    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_10/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
    {
    -1.65
    our
    -1.62
     nôtre
    -1.51
    蠵
    -1.47
     kotak
    -1.43
    两者
    -1.41
    ICIENCY
    -1.40
    我们
    -1.40
     нашел
    -1.38
    AND
    -1.36
    POSITIVE LOGITS
     enough
    1.80
     that
    1.66
    <bos>
    1.52
     suficiente
    1.41
    istiwa
    1.40
     sufficient
    1.38
     which
    1.37
     qualcuno
    1.29
     alguien
    1.29
     its
    1.28
    Activations Density 0.030%

    No Known Activations