© 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. 110972
    Prev
    Next
    INDEX
    Explanations

    constantly evolving or improving

    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
    zugehen
    -1.20
    始めた
    -1.08
     finally
    -1.05
    zielle
    -1.03
     demokra
    -1.03
    laş
    -1.02
    常用的
    -1.02
    Enfin
    -1.01
    zake
    -1.01
    などが
    -1.00
    POSITIVE LOGITS
     evolving
    1.47
     striving
    1.38
     strive
    1.37
     improving
    1.25
     changing
    1.23
    不断的
    1.20
     updated
    1.18
    constant
    1.16
     strives
    1.16
     replen
    1.16
    Activations Density 0.032%

    No Known Activations