© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 51843
    Prev
    Next
    INDEX
    Explanations

    treasure, treasury, trove

    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_65k_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
     अणु
    0.44
    atives
    0.43
    빅
    0.41
     químicos
    0.40
    itatively
    0.40
     ATC
    0.39
     Excuse
    0.38
     Astrology
    0.38
     വിവാ
    0.38
    riages
    0.38
    POSITIVE LOGITS
     treasure
    1.56
    treasure
    1.36
     Treasure
    1.25
     treasures
    1.24
     treas
    1.17
     treasury
    1.13
     trove
    1.12
    宝
    1.11
    Treas
    1.08
    treas
    0.98
    Activations Density 0.025%

    No Known Activations