© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18751
    Prev
    Next
    INDEX
    Explanations

    reduce, minimize, decrease

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pickups
    0.42
     нара
    0.42
     ***!
    0.42
    oczy
    0.41
     확장
    0.40
    糍
    0.39
    मारा
    0.39
    _{+}$
    0.39
     Rookie
    0.39
    加热
    0.39
    POSITIVE LOGITS
    Subtract
    0.92
     subtract
    0.91
     subtracted
    0.90
     Subtract
    0.89
     decrease
    0.88
     subtracting
    0.87
    減少
    0.84
    decrease
    0.82
     decreases
    0.81
     subtraction
    0.80
    Activations Density 0.175%

    No Known Activations