© 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-262K
    7. 4727
    Prev
    Next
    INDEX
    Explanations

    pronoun-verb contractions

    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
    认为
    0.20
     These
    0.19
    、
    0.19
    ，
    0.18
    choose
    0.18
    認為
    0.18
     ,
    0.17
     considère
    0.17
    dealing
    0.17
    Са
    0.17
    POSITIVE LOGITS
     isn
    0.22
     είναι
    0.21
    จะไม่
    0.21
     brukes
    0.21
     есть
    0.20
     दिखने
    0.19
     není
    0.19
    াইব
    0.19
    ી
    0.19
     будет
    0.18
    Activations Density 0.401%

    No Known Activations