© 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. 41-GEMMASCOPE-2-RES-262K
    7. 61222
    Prev
    Next
    INDEX
    Explanations

    ss it

    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_all/layer_41_width_262k_l0_big
    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
     Heavenly
    0.41
    ⌵
    0.41
     ஹீ
    0.40
     término
    0.39
     एडिशन
    0.39
     ह्यू
    0.39
    ᠩ
    0.38
    Hollywood
    0.38
    ément
    0.38
    𝘦
    0.38
    POSITIVE LOGITS
    WAT
    0.46
    Pier
    0.40
     Catalunya
    0.40
     WAT
    0.39
    CAT
    0.38
     legitim
    0.38
     GATE
    0.38
     devoted
    0.37
     CAT
    0.37
     devotes
    0.37
    Activations Density 0.001%

    No Known Activations