© 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-262K
    7. 27225
    Prev
    Next
    INDEX
    Explanations

    for [pronoun/gerund]

    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
     ለማ
    0.51
    a
    0.50
     ನೋಡ
    0.48
     감사
    0.48
     추가
    0.47
     ம
    0.47
     തവണ
    0.47
     இத
    0.46
    spruch
    0.45
     declaración
    0.45
    POSITIVE LOGITS
     being
    0.61
    being
    0.55
     fiind
    0.53
     étant
    0.46
     способность
    0.44
     lack
    0.44
    其
    0.43
    Being
    0.43
     BEING
    0.43
     succesfully
    0.43
    Activations Density 0.023%

    No Known Activations