© 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. 409
    Prev
    Next
    INDEX
    Explanations

    Terminator and related concepts

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

    references to dates, years, and timestamps, particularly in numerical format.

    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_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
     courseId
    -0.82
     propre
    -0.77
     retorted
    -0.76
    Hamlet
    -0.76
     sostenible
    -0.75
    krä
    -0.73
     team
    -0.73
    teamId
    -0.73
    ลม
    -0.71
     freue
    -0.71
    POSITIVE LOGITS
     Terminator
    1.35
     terminator
    1.20
     Termin
    1.20
    Terminator
    1.06
    terminator
    1.03
     TERMIN
    1.02
    termin
    1.00
     machines
    0.98
    machines
    0.90
    Termin
    0.89
    Activations Density 0.015%

    No Known Activations