© 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. 31-GEMMASCOPE-2-RES-262K
    7. 168979
    Prev
    Next
    INDEX
    Explanations

    state or discovery of something

    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
    育
    0.42
     крови
    0.42
    isAdmin
    0.42
     Lobby
    0.40
    ër
    0.39
    nti
    0.39
    loir
    0.39
    leva
    0.39
    irc
    0.38
    eri
    0.38
    POSITIVE LOGITS
    전에
    0.49
    OTOS
    0.47
    する場合
    0.47
     például
    0.46
    ﻜ
    0.45
     vooraf
    0.45
     destroy
    0.44
     excursions
    0.44
     اہل
    0.42
     před
    0.42
    Activations Density 0.017%

    No Known Activations