© 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. 190532
    Prev
    Next
    INDEX
    Explanations

    pictures, petition, appropriate, outbursts

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

    hypopyon, words died, India surpassed, pausing to

    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
    金
    0.47
    人和
    0.44
    อะไร
    0.41
     luggage
    0.40
     Chocol
    0.40
    Xc
    0.40
    亼
    0.40
     एजुकेशन
    0.39
     получения
    0.39
     Snakes
    0.39
    POSITIVE LOGITS
     reducir
    0.55
     ridurre
    0.50
     reduzir
    0.48
     メール
    0.48
     riego
    0.45
     сверх
    0.43
    頓
    0.42
    gleich
    0.42
     réduire
    0.42
    wunsch
    0.42
    Activations Density 0.000%

    No Known Activations