© 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. 34-GEMMASCOPE-RES-131K
    7. 60514
    Prev
    Next
    INDEX
    Explanations

    counting numbers and identifiers

    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_34/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
     so
    -1.39
     as
    -1.28
     v
    -1.09
    felizmente
    -1.08
     f
    -1.08
     by
    -1.05
     (
    -1.02
     does
    -1.02
     easy
    -1.01
     способом
    -1.01
    POSITIVE LOGITS
     ۱۰
    1.66
    ⑩
    1.56
     tenth
    1.50
    ۱۰
    1.47
     ten
    1.34
     Tenth
    1.23
    🕙
    1.22
    十
    1.17
     dieci
    1.16
    小麦
    1.15
    Activations Density 0.054%

    No Known Activations