© 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. 22-GEMMASCOPE-RES-131K
    4. 12188
    Prev
    Next
    INDEX
    Explanations

    chinese given names and surnames

    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_22/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
     and
    -1.51
     your
    -1.42
     told
    -1.33
     freaking
    -1.30
     my
    -1.27
     小学生
    -1.27
     dejar
    -1.25
     a
    -1.24
     an
    -1.21
    為に
    -1.19
    POSITIVE LOGITS
    鮡
    1.57
     作り方
    1.54
     impecable
    1.51
     hemd
    1.47
    athered
    1.43
     configurações
    1.41
     sisält
    1.41
     slutet
    1.39
     åren
    1.35
     kveld
    1.34
    Activations Density 0.013%

    No Known Activations