© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 602
    Prev
    Next
    INDEX
    Explanations

    ре / Ré 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_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
    -
    -3.08
    䊐
    -2.97
     dreary
    -2.64
     anzunehmen
    -2.44
    が好き
    -2.38
    先是
    -2.38
     Then
    -2.34
     связанные
    -2.33
    了一个
    -2.30
     hefty
    -2.28
    POSITIVE LOGITS
     argentina
    2.81
    ⢌
    2.59
    mathrm
    2.50
    '
    2.42
    u
    2.39
    </h1>
    2.38
    蓆
    2.38
    缐
    2.30
     sewa
    2.28
    洨
    2.20
    Activations Density 0.001%

    No Known Activations