© 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. 40-GEMMASCOPE-2-RES-65K
    7. 53355
    Prev
    Next
    INDEX
    Explanations

    Nobel Prizes

    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
    旗舰
    0.44
    矿
    0.43
    ገድ
    0.43
    冦
    0.42
    вяз
    0.41
    彥
    0.41
    ज़न
    0.41
     देवगन
    0.40
    eterminate
    0.40
    窑
    0.40
    POSITIVE LOGITS
     Nobel
    1.59
    Nob
    1.45
     Nob
    1.13
    nob
    1.12
     nob
    0.98
     awarded
    0.86
     Noble
    0.79
     laure
    0.77
     awarding
    0.77
    Noble
    0.77
    Activations Density 0.013%

    No Known Activations