© 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. 15838
    Prev
    Next
    INDEX
    Explanations

    opposite mode responses

    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
     ر
    0.41
     Unter
    0.40
     Only
    0.38
     פי
    0.38
     و
    0.37
     آ
    0.37
     Land
    0.37
    yness
    0.37
     Trans
    0.37
     אותו
    0.37
    POSITIVE LOGITS
     excluded
    0.38
     avoided
    0.38
     ген
    0.38
     decreases
    0.37
    excluded
    0.37
     genotype
    0.37
    咱們
    0.37
    валось
    0.36
    鎊
    0.36
    кты
    0.36
    Activations Density 0.001%

    No Known Activations