© 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. 8487
    Prev
    Next
    INDEX
    Explanations

    phone download games

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

    conversational phrases in multiple languages

    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
    হইল
    0.53
     хірур
    0.51
    URNIZ
    0.50
    幀
    0.50
    原子力
    0.50
     Nucleaire
    0.49
    境界層
    0.48
     demonstrable
    0.48
     fondamentali
    0.48
     своїх
    0.48
    POSITIVE LOGITS
    小编
    0.70
    0.61
    k
    0.60
     bạn
    0.60
     popular
    0.57
     ඔබට
    0.57
    popular
    0.55
    ท่าน
    0.55
     https
    0.55
      
    0.54
    Activations Density 0.014%

    No Known Activations