© 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. 14137
    Prev
    Next
    INDEX
    Explanations

    end times, large systems, existentialism

    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
     linh
    0.51
     kullanımı
    0.50
     ex
    0.48
     lini
    0.46
    滟
    0.46
     nd
    0.46
    ྰ
    0.46
    來越
    0.45
     ș
    0.45
     pikir
    0.45
    POSITIVE LOGITS
    butt
    0.53
    К
    0.49
    нак
    0.49
    bus
    0.48
    과학
    0.46
    вен
    0.45
     enriching
    0.45
    bation
    0.45
    এস
    0.45
    ГЭ
    0.45
    Activations Density 0.004%

    No Known Activations