© 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
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 13804
    Prev
    Next
    INDEX
    Explanations

    Japanese verbs end in "-u" or "-su"

    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_53_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
     Št
    0.49
     fác
    0.48
     Dí
    0.45
     Š
    0.45
    Ϊ
    0.45
    쏠
    0.44
     Séb
    0.43
    Š
    0.43
    Ș
    0.43
     Már
    0.42
    POSITIVE LOGITS
    toire
    0.56
     wo
    0.50
    ありません
    0.47
    utte
    0.46
     mae
    0.45
     ware
    0.45
    imas
    0.44
    iru
    0.44
     rom
    0.44
    持って
    0.43
    Activations Density 0.021%

    No Known Activations