© 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-262K
    7. 99773
    Prev
    Next
    INDEX
    Explanations

    **Not** rigidly straight

    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_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
    Հ
    0.52
    দীর্ঘ
    0.47
    TextureAsset
    0.47
    दर्द
    0.46
    ཥ
    0.46
    퐫
    0.46
    ീതി
    0.45
    িষ্ট
    0.45
    娀
    0.45
    র্পণ
    0.44
    POSITIVE LOGITS
    ни
    0.54
    ill
    0.52
     Daher
    0.49
    ens
    0.46
     daher
    0.46
    sh
    0.45
     поэтому
    0.45
    au
    0.44
     meines
    0.43
     zoomed
    0.42
    Activations Density 0.003%

    No Known Activations