© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 13749
    Prev
    Next
    INDEX
    Explanations

    fantasy names and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    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
    櫸
    0.51
    發展
    0.50
    甲基
    0.50
    基督教
    0.47
    業務
    0.47
     propried
    0.45
    تيب
    0.45
    廰
    0.44
     bairro
    0.44
    犟
    0.44
    POSITIVE LOGITS
     sprites
    0.63
     runes
    0.63
    Elemental
    0.59
     mage
    0.57
     shards
    0.57
     Warhammer
    0.57
    Death
    0.55
     rune
    0.55
     nebula
    0.54
     arcane
    0.54
    Activations Density 0.048%

    No Known Activations