© 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. 5990
    Prev
    Next
    INDEX
    Explanations

    explicitly prohibit or prioritize safety

    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
     από
    0.31
    對
    0.30
    যখন
    0.30
     což
    0.29
     harmony
    0.29
     với
    0.28
     for
    0.28
    喜歡
    0.28
     on
    0.28
    動
    0.28
    POSITIVE LOGITS
    cheduling
    0.28
    LoopBlend
    0.27
    ajada
    0.27
    :");
    0.27
    initis
    0.27
     uintptr
    0.26
    would
    0.25
    Xaml
    0.25
     Ouvrard
    0.25
    þ
    0.25
    Activations Density 0.065%

    No Known Activations