© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5236
    Prev
    Next
    INDEX
    Explanations

    determiners followed by nouns

    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
     اینکه
    0.59
     whose
    0.55
     которые
    0.54
     όπου
    0.51
     which
    0.48
     которыми
    0.47
     که
    0.47
    雖
    0.47
     with
    0.46
    》，
    0.46
    POSITIVE LOGITS
     pueda
    0.57
     potuto
    0.53
     underlies
    0.49
     pudiera
    0.48
    soever
    0.47
    人都
    0.46
     ordinateur
    0.46
    と思いました
    0.46
    人は
    0.44
     ماہر
    0.44
    Activations Density 0.284%

    No Known Activations