© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1909
    Prev
    Next
    INDEX
    Explanations

    idiomatic two-word phrases

    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
     l
    0.55
    v
    0.51
    ization
    0.50
    sorted
    0.49
    izar
    0.48
     favoring
    0.48
    ustering
    0.48
    italic
    0.47
    it
    0.47
     in
    0.47
    POSITIVE LOGITS
    া
    0.63
    ा
    0.54
    ה
    0.52
    仔
    0.49
    ྥ
    0.49
    νο
    0.48
    Ꭹ
    0.48
    ప
    0.48
     ван
    0.46
     территориа
    0.46
    Activations Density 0.460%

    No Known Activations