© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17368
    Prev
    Next
    INDEX
    Explanations

    current events and status

    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
     "
    0.44
     pouvait
    0.43
     when
    0.42
    当时
    0.41
     podía
    0.39
     O
    0.38
    还可以
    0.38
     C
    0.38
     I
    0.38
     Peppers
    0.38
    POSITIVE LOGITS
     atualmente
    0.69
     obecnie
    0.68
     attualmente
    0.66
     telah
    0.63
     derzeit
    0.63
     ఇటీవల
    0.63
     sedang
    0.61
    현재
    0.61
     ప్రస్తుతం
    0.61
     ಈಗಾಗಲೇ
    0.59
    Activations Density 0.039%

    No Known Activations