© 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. 10252
    Prev
    Next
    INDEX
    Explanations

    the phrase or concept

    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
     influences
    0.23
    {
    0.22
     therapy
    0.21
     introduction
    0.21
     abortion
    0.21
     Bags
    0.21
     digestion
    0.21
     bags
    0.20
     >=
    0.20
     dioxide
    0.20
    POSITIVE LOGITS
    Ссылка
    0.25
    ニュ
    0.25
    rekli
    0.24
    ༣
    0.24
    ﺳ
    0.23
    メ
    0.23
    гі
    0.22
    Ᏻ
    0.22
    ترنت
    0.22
     countryside
    0.22
    Activations Density 0.234%

    No Known Activations