© 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. 64039
    Prev
    Next
    INDEX
    Explanations

    defense and protection

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

    technical terms in game mechanics, computing, and specialized domains.

    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
    ATTACK
    -1.04
     Attack
    -0.94
     attacking
    -0.93
     ATTACK
    -0.92
     attack
    -0.91
     atk
    -0.90
    attack
    -0.83
    攻撃
    -0.83
     sharps
    -0.83
     enlistment
    -0.82
    POSITIVE LOGITS
     defensive
    1.57
     resistance
    1.57
     defense
    1.55
     defence
    1.45
     resistances
    1.41
     protection
    1.34
     defenses
    1.32
     Resistance
    1.25
     shield
    1.23
     resistant
    1.20
    Activations Density 0.006%

    No Known Activations