© 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. 224275
    Prev
    Next
    INDEX
    Explanations

    specific locations or items

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

    complex interplay of circumstances

    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
     ಗೊ
    0.49
     Polymers
    0.49
    লগ্ন
    0.49
    ংখ্যান
    0.49
     আইডিয়া
    0.48
     Photon
    0.47
     Charan
    0.47
    𝙇
    0.47
    rtle
    0.47
    t
    0.46
    POSITIVE LOGITS
     chaos
    0.43
     σήμερα
    0.43
     straighten
    0.42
    标题
    0.41
     crosstalk
    0.41
     chaotic
    0.40
     apologize
    0.39
     sneaky
    0.39
     penalty
    0.38
     đủ
    0.38
    Activations Density 0.001%

    No Known Activations