© 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-65K
    7. 28377
    Prev
    Next
    INDEX
    Explanations

    complex words, foreign languages, or specific continuations

    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_65k_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
    ៤
    0.46
     $^{
    0.42
    <0x85>
    0.40
    ulation
    0.39
     гаран
    0.39
    ुरु
    0.39
    ᡧ
    0.38
     immunology
    0.38
    yendo
    0.37
     pathogenicity
    0.37
    POSITIVE LOGITS
    я
    0.49
     größte
    0.48
     void
    0.48
     พวก
    0.47
     hoge
    0.47
     вони
    0.47
     อย่าง
    0.45
     Unless
    0.45
     مہارت
    0.45
     grootste
    0.45
    Activations Density 0.016%

    No Known Activations