© 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. 34-GEMMASCOPE-RES-131K
    4. 110549
    Prev
    Next
    INDEX
    Explanations

    industry news and sectors

    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
     peuples
    -1.00
     the
    -1.00
    変わらず
    -0.98
     ewigen
    -0.96
    过程中
    -0.96
     instituted
    -0.93
     וב
    -0.93
    アレンジ
    -0.90
     dân
    -0.89
    本当の
    -0.89
    POSITIVE LOGITS
     sectors
    1.69
     sector
    1.63
    wide
    1.63
    sector
    1.30
    industry
    1.27
     industry
    1.25
     segment
    1.20
     Sector
    1.13
     vertical
    1.11
     giants
    1.11
    Activations Density 0.023%

    No Known Activations