© 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. 83313
    Prev
    Next
    INDEX
    Explanations

    brand names and products

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

    possession of final stage supporting stem

    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
    å
    0.51
    開発
    0.48
     kudu
    0.47
    せ
    0.46
    いつ
    0.46
    ク
    0.46
    ち
    0.46
    スパ
    0.44
    アー
    0.43
    Coroutine
    0.43
    POSITIVE LOGITS
     Какие
    0.52
     Мин
    0.47
     Министерства
    0.46
    atorias
    0.46
     मेहन
    0.45
     wirken
    0.45
     याबाबत
    0.44
     Nahrung
    0.44
     त्यानुसार
    0.44
     Эти
    0.42
    Activations Density 0.003%

    No Known Activations