© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65013
    Prev
    Next
    INDEX
    Explanations

    life stages and milestones

    np_acts-logits-general · gemini-2.5-flash-lite

    words and concepts related to work, jobs, and employment.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     uur
    -1.27
     procha
    -1.25
     tages
    -1.23
     oled
    -1.23
     kalender
    -1.23
     vider
    -1.20
     daga
    -1.19
     niedersachsen
    -1.17
     staffel
    -1.16
     jorge
    -1.13
    POSITIVE LOGITS
     start
    1.64
     starts
    1.51
     if
    1.45
     begins
    1.45
     first
    1.44
     information
    1.41
     or
    1.39
     would
    1.38
     started
    1.38
     presence
    1.37
    Activations Density 0.073%

    No Known Activations