© 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. 250868
    Prev
    Next
    INDEX
    Explanations

    median annual salary

    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
    ח
    0.61
    ไม
    0.58
    ת
    0.55
    מר
    0.52
    לי
    0.51
    מ
    0.51
    า
    0.50
    כ
    0.50
    йт
    0.49
    ੰਜ
    0.49
    POSITIVE LOGITS
     duplex
    0.46
     discontinuation
    0.45
     rental
    0.41
     uninterrupted
    0.41
     faucet
    0.40
     senza
    0.40
     আদৌ
    0.40
     discontinued
    0.39
     Mini
    0.39
     Rental
    0.39
    Activations Density 0.000%

    No Known Activations