© 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. 34-GEMMASCOPE-RES-131K
    7. 107066
    Prev
    Next
    INDEX
    Explanations

    living state or surroundings

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

    the word "living" and its related phrases, particularly in contexts of living spaces and living conditions.

    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
     komplette
    -1.02
    デッキ
    -0.85
     stock
    -0.84
     partire
    -0.81
     Bever
    -0.81
     gegeben
    -0.80
    لیت
    -0.80
     жителей
    -0.80
    ButtonModule
    -0.79
     Sched
    -0.79
    POSITIVE LOGITS
     quarters
    1.30
     expenses
    1.24
     wage
    1.15
     arrangement
    1.09
     conditions
    1.05
     arrangements
    1.04
     spaces
    1.00
     Wage
    0.97
     standards
    0.96
     Standards
    0.95
    Activations Density 0.015%

    No Known Activations