© 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-16K
    7. 1139
    Prev
    Next
    INDEX
    Explanations

    erasing karma

    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_16k_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
    ুক্তি
    0.43
    岧
    0.41
    нтэр
    0.40
     آہستہ
    0.40
    летие
    0.39
     ബ്രി
    0.39
     யூ
    0.39
     गणेश
    0.38
    艐
    0.38
     खोसला
    0.38
    POSITIVE LOGITS
    變得
    0.45
     বিকেল
    0.42
     Belgian
    0.42
    vos
    0.42
     triples
    0.42
     caught
    0.41
     bouquets
    0.41
    IB
    0.41
     Belgium
    0.40
    POP
    0.40
    Activations Density 0.114%

    No Known Activations