© 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. 24155
    Prev
    Next
    INDEX
    Explanations

    SQL database access

    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
     Mundo
    0.40
     dünyanın
    0.39
     Bilbao
    0.38
     Dunia
    0.38
     Welt
    0.38
    雒
    0.37
    ኣ
    0.37
     Svet
    0.37
     convivencia
    0.37
     Mundial
    0.36
    POSITIVE LOGITS
     ancients
    0.42
    ェ
    0.42
     slender
    0.42
     požad
    0.40
    قدر
    0.40
     retirement
    0.40
     solidification
    0.40
     fouling
    0.39
     silicone
    0.39
     sacrificial
    0.39
    Activations Density 0.000%

    No Known Activations