© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 164684
    Prev
    Next
    INDEX
    Explanations

    differences between

    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_262k_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
     $(`.
    0.43
    akanan
    0.36
     사용하여
    0.36
    เดียวกัน
    0.36
    椀
    0.36
     queryObject
    0.35
     сфе
    0.35
    Ϲ
    0.34
    :"))
    0.34
     Kxb
    0.34
    POSITIVE LOGITS
     waivers
    0.41
     virtue
    0.40
     waiting
    0.39
     जमी
    0.39
     dating
    0.38
     Southern
    0.38
    waiting
    0.38
     waiver
    0.37
     اح
    0.37
     campuses
    0.37
    Activations Density 0.000%

    No Known Activations