© 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-65K
    7. 40228
    Prev
    Next
    INDEX
    Explanations

    conditions leading to something else

    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
    Stock
    0.52
    ﻘ
    0.50
     Bunker
    0.49
    Chunks
    0.49
    Tickets
    0.47
     നടത്തിയ
    0.47
    G
    0.46
     Cells
    0.46
     Quinn
    0.46
    Buck
    0.46
    POSITIVE LOGITS
    ंदाज
    0.53
    箴
    0.43
     {:
    0.42
     kompak
    0.42
     protrusions
    0.41
    िड
    0.41
     parfois
    0.41
     crashes
    0.40
     parametrization
    0.40
     parâmetros
    0.39
    Activations Density 0.033%

    No Known Activations