© 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. 721
    Prev
    Next
    INDEX
    Explanations

    section headers and metadata

    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
    仉
    -1.37
    ゼル
    -1.35
     folly
    -1.30
     edades
    -1.28
    Ꮙ
    -1.24
    Zh
    -1.23
    gericht
    -1.22
    Weiß
    -1.21
     moisturizer
    -1.20
    kein
    -1.20
    POSITIVE LOGITS
    ブログ村
    1.44
     umożli
    1.40
     never
    1.38
    が欲しい
    1.37
     zwykle
    1.35
     pozw
    1.33
    刧
    1.32
     siendo
    1.31
     zobac
    1.31
    骤
    1.30
    Activations Density 0.001%

    No Known Activations