© 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. 120103
    Prev
    Next
    INDEX
    Explanations

    various differences

    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
     to
    -1.64
     this
    -1.64
    ּוֹ
    -1.33
     like
    -1.28
    voegd
    -1.27
    érez
    -1.25
    了不少
    -1.20
     it
    -1.20
    はこんな感じ
    -1.20
    <eos>
    -1.19
    POSITIVE LOGITS
    我已经
    1.38
    உ
    1.35
    さまざまな
    1.35
    ׇ
    1.34
    Different
    1.31
    丰富的
    1.31
     從
    1.29
    ští
    1.28
    vlád
    1.27
    诸多
    1.27
    Activations Density 0.165%

    No Known Activations