© 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-65K
    7. 17357
    Prev
    Next
    INDEX
    Explanations

    verb tense and grammar

    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_65k_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
    vature
    0.45
    類
    0.45
    attr
    0.42
    acceler
    0.42
    万
    0.41
    스템
    0.39
     肉
    0.39
    萬
    0.39
    hops
    0.39
    モン
    0.38
    POSITIVE LOGITS
     subjunctive
    0.73
     emphasize
    0.54
     present
    0.52
     emphasized
    0.51
     emphasise
    0.51
     enfat
    0.51
     emphasizes
    0.49
    语气
    0.49
     emphatic
    0.48
     emphasis
    0.48
    Activations Density 0.220%

    No Known Activations