© 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. 113507
    Prev
    Next
    INDEX
    Explanations

    rebounding, heading, ball

    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
     گذر
    0.43
     سلو
    0.41
     이동
    0.41
    燒
    0.40
    solo
    0.40
     punished
    0.39
     تقل
    0.39
     Spo
    0.38
     counterfeit
    0.38
    flush
    0.38
    POSITIVE LOGITS
    捞
    0.48
    Protein
    0.45
     Station
    0.45
    ்ப
    0.45
     aerial
    0.43
    गिरी
    0.42
     Astronomy
    0.40
    Warehouse
    0.40
     Associação
    0.40
     प्रोटीन
    0.40
    Activations Density 0.018%

    No Known Activations