© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 2251
    Prev
    Next
    INDEX
    Explanations

    have something

    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
    ード
    0.30
    Coc
    0.30
    ў
    0.29
    for
    0.28
    有
    0.28
     Gefahr
    0.28
    可能性
    0.27
    м
    0.27
     lacking
    0.27
    да
    0.26
    POSITIVE LOGITS
     recours
    0.57
     pretensions
    0.55
     recourse
    0.53
     nevoie
    0.51
     accès
    0.50
     difficulty
    0.49
     bisogno
    0.47
     leeway
    0.46
     patience
    0.45
     acesso
    0.45
    Activations Density 0.250%

    No Known Activations