© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27139
    Prev
    Next
    INDEX
    Explanations

    protection, defense, resistance

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

    terminology related to defense or protection systems, including barriers, inhibitors, shields, and defensive mechanisms.

    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
    galkan
    -1.00
     Aufenthalts
    -0.97
    uete
    -0.95
    anias
    -0.94
    riente
    -0.94
    𝒂
    -0.93
    melis
    -0.91
     Dokumentation
    -0.91
    ඹ
    -0.90
     fontaine
    -0.89
    POSITIVE LOGITS
     protecting
    2.45
     protection
    2.42
     protects
    2.09
     protect
    2.05
     protective
    1.88
    protection
    1.83
     defending
    1.74
     protezione
    1.73
     proteger
    1.73
     defense
    1.66
    Activations Density 0.210%

    No Known Activations