© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1060
    Prev
    Next
    INDEX
    Explanations

    python code

    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_31_width_16k_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
    ('>
    0.40
    coef
    0.39
    lhe
    0.39
    webElementXpaths
    0.39
    ailles
    0.38
    olls
    0.37
    atthena
    0.37
     prerog
    0.37
    elands
    0.37
    elni
    0.37
    POSITIVE LOGITS
    における
    0.49
     utilizzare
    0.49
     Tentang
    0.46
     ב
    0.45
     lernen
    0.44
     newbie
    0.42
    પ
    0.42
    ంలోని
    0.42
    カ
    0.41
     中的
    0.41
    Activations Density 0.530%

    No Known Activations