© 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. 16-GEMMASCOPE-2-RES-65K
    7. 630
    Prev
    Next
    INDEX
    Explanations

    and [thing]

    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_16_width_65k_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
    し
    0.61
    ystem
    0.51
    с
    0.48
    ästä
    0.47
     své
    0.46
    ுக
    0.46
     Я
    0.45
    ได้
    0.45
     этих
    0.45
    ه‌ای
    0.44
    POSITIVE LOGITS
    9
    0.50
     mediocr
    0.45
    ၉
    0.44
     a
    0.44
     virulence
    0.44
     ხელისუფლების
    0.43
     hallucinations
    0.43
     apathy
    0.42
     turbulence
    0.42
     nausea
    0.42
    Activations Density 0.448%

    No Known Activations