© 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. 27972
    Prev
    Next
    INDEX
    Explanations

    HTML styling

    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
    también
    0.46
    え
    0.45
    éléments
    0.45
    ᱐
    0.44
     vật
    0.44
     анти
    0.43
    Underwater
    0.43
     prostaglandins
    0.43
     বাতাস
    0.43
     점
    0.42
    POSITIVE LOGITS
    lee
    0.41
     TL
    0.37
    cla
    0.37
     decidió
    0.36
    lyl
    0.36
     پیروی
    0.36
    influenced
    0.36
     grossly
    0.36
    cco
    0.35
    cec
    0.35
    Activations Density 0.015%

    No Known Activations