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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 181810
    Prev
    Next
    INDEX
    Explanations

    medical, legal, or technical references

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers and descriptive terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     указывает
    0.49
     преда
    0.45
     иностран
    0.45
    sync
    0.44
    窠
    0.42
     مرا
    0.41
     এরা
    0.40
     Watering
    0.40
     ليس
    0.39
    άνει
    0.39
    POSITIVE LOGITS
    으
    0.48
    ご
    0.48
    庁
    0.47
    \
    0.47
     TORT
    0.46
    kana
    0.44
    으로
    0.44
    मै
    0.44
    知
    0.43
    로
    0.43
    Activations Density 0.000%

    No Known Activations