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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 211629
    Prev
    Next
    INDEX
    Explanations

    past tense verb continuations

    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_40_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
     Illustrations
    0.42
     Magazines
    0.39
     Neither
    0.38
    亙
    0.38
     Watering
    0.38
     lernen
    0.37
    ڪ
    0.37
     ancestors
    0.36
     Änder
    0.36
     seashore
    0.36
    POSITIVE LOGITS
    ネタ
    0.40
    내
    0.39
    本
    0.38
    인
    0.36
     ഒറ്റ
    0.36
     either
    0.36
    明
    0.35
     Giles
    0.35
     التواصل
    0.35
    尃
    0.35
    Activations Density 0.109%

    No Known Activations