© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7263
    Prev
    Next
    INDEX
    Explanations

    durability and resistance

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

    robust and durable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jährigen
    0.43
    хара
    0.42
    忿
    0.42
    раў
    0.42
     Бушлай
    0.41
    统一
    0.40
     демокра
    0.40
    규모
    0.39
    渲
    0.39
    ตอน
    0.39
    POSITIVE LOGITS
     durability
    0.89
     durable
    0.77
     withstand
    0.75
     resilient
    0.70
     resilience
    0.68
     Durable
    0.67
     resistant
    0.67
     resistance
    0.64
    耐
    0.64
     indestruct
    0.63
    Activations Density 0.194%

    No Known Activations