© 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. 47924
    Prev
    Next
    INDEX
    Explanations

    color codes and styles

    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
    ு
    0.39
    oked
    0.39
    сора
    0.38
    ju
    0.38
     максимум
    0.38
     अवधि
    0.37
    tej
    0.36
    '।
    0.35
    '.'
    0.35
    य्
    0.35
    POSITIVE LOGITS
    𝐑
    0.42
     åter
    0.41
     दीप
    0.40
     COMPAR
    0.38
     vécu
    0.37
    닐
    0.37
    Prescott
    0.37
     Plessis
    0.36
     برگ
    0.36
     convi
    0.36
    Activations Density 0.011%

    No Known Activations