© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 8759
    Prev
    Next
    INDEX
    Explanations

    violating ethical principles or guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
     связь
    1.07
     efecto
    1.05
     efeito
    1.00
     trouble
    0.97
     обновление
    0.96
     г
    0.95
     информация
    0.94
     spouse
    0.93
     effetto
    0.88
     future
    0.87
    POSITIVE LOGITS
    Principles
    1.19
     tenets
    1.17
    standards
    1.17
     Principles
    1.17
     precepts
    1.15
     principles
    1.14
    א
    1.12
    నీ
    1.11
     standards
    1.10
    ി
    1.08
    Activations Density 0.261%

    No Known Activations