© 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-16K
    7. 457
    Prev
    Next
    INDEX
    Explanations

    during or when

    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_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
     salaried
    0.30
     hardship
    0.29
     fraudulent
    0.29
     blatantly
    0.29
     entrusted
    0.29
     mutilated
    0.29
    whose
    0.28
     "_
    0.27
    cknowled
    0.27
    함으로써
    0.27
    POSITIVE LOGITS
     during
    0.57
     durante
    0.56
     quando
    0.52
     cuando
    0.52
     podczas
    0.52
     tijdens
    0.52
     when
    0.51
     během
    0.49
     когда
    0.48
     lors
    0.47
    Activations Density 1.730%

    No Known Activations