© 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. 14173
    Prev
    Next
    INDEX
    Explanations

    search and stories

    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
     अजून
    0.59
     கட்டமை
    0.57
     அடிப்படை
    0.57
     אנחנו
    0.57
     இன்னும்
    0.54
    叁
    0.53
     மின்ன
    0.52
     внутріш
    0.52
    儼
    0.52
     করছি
    0.51
    POSITIVE LOGITS
     robbers
    0.59
     oxen
    0.56
     villagers
    0.51
     peasant
    0.48
     fisherman
    0.47
     goat
    0.47
     leprosy
    0.47
     weeping
    0.46
     cunning
    0.46
     village
    0.46
    Activations Density 0.045%

    No Known Activations