© 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-65K
    7. 10509
    Prev
    Next
    INDEX
    Explanations

    relative clauses starting with which

    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_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
    न
    0.63
    ن
    0.56
    ให้กับ
    0.54
     teníamos
    0.54
    ként
    0.53
    那里
    0.52
     இல்லாத
    0.52
    ಿರುವ
    0.51
    IN
    0.51
    ☜
    0.51
    POSITIVE LOGITS
    soever
    0.57
    之地
    0.50
    তে
    0.49
     are
    0.47
     resten
    0.47
    epe
    0.46
    VERY
    0.46
    توى
    0.45
    are
    0.44
     to
    0.44
    Activations Density 0.037%

    No Known Activations