© 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. 143957
    Prev
    Next
    INDEX
    Explanations

    southern part, babies from

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

    discover machine, KPIs &

    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
     موب
    0.55
     cuentan
    0.52
    am
    0.51
    archivo
    0.48
     आग
    0.46
    ously
    0.46
     Playstation
    0.45
    ﺐ
    0.44
     κάνει
    0.43
     forward
    0.43
    POSITIVE LOGITS
    lici
    0.46
     Baltes
    0.46
    糜
    0.43
     సార
    0.43
     Menz
    0.43
    Примечания
    0.42
     CURLE
    0.41
    牷
    0.41
     मिळाल
    0.41
     Balashov
    0.41
    Activations Density 0.000%

    No Known Activations