© 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. 93156
    Prev
    Next
    INDEX
    Explanations

    menu states

    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
     शर्ट
    0.47
    机场
    0.44
    房地产
    0.44
     étoile
    0.40
    毂
    0.40
    鬓
    0.40
    थिंग
    0.40
     पिंक
    0.40
     pakk
    0.40
    教会
    0.39
    POSITIVE LOGITS
     ventricular
    0.52
    s
    0.51
     plunger
    0.50
    чення
    0.47
     gluten
    0.47
     carbur
    0.46
     regenerative
    0.45
     ANZ
    0.45
    れた
    0.45
    ים
    0.44
    Activations Density 0.001%

    No Known Activations