© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 556
    Prev
    Next
    INDEX
    Explanations

    spar, sparring, sparql, sparrow, sparling, sparsity

    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
    焄
    -2.91
    ↵
    -2.56
    錵
    -2.38
    龵
    -2.33
     servici
    -2.33
    ⛦
    -2.33
     armar
    -2.31
     alarme
    -2.30
    谖
    -2.28
    萣
    -2.25
    POSITIVE LOGITS
    当然
    3.08
    st
    2.72
    ="
    2.52
    "
    2.47
    珦
    2.39
    на
    2.34
     Similarly
    2.31
     he
    2.31
    x
    2.23
    {
    2.17
    Activations Density 0.003%

    No Known Activations