© 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-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167245
    Prev
    Next
    INDEX
    Explanations

    durability and resilience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sunset
    0.40
     kills
    0.38
     alcohol
    0.37
     sunrise
    0.37
     dnes
    0.37
     sunsets
    0.37
     ၀
    0.37
     dismissed
    0.36
     Sury
    0.36
     sim
    0.35
    POSITIVE LOGITS
    欢迎
    0.38
     durable
    0.37
     Hardy
    0.37
    ຂໍ
    0.36
     toughest
    0.36
    莼
    0.36
    safety
    0.35
     hardy
    0.35
     espada
    0.35
     durability
    0.35
    Activations Density 0.003%

    No Known Activations