© 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. 107942
    Prev
    Next
    INDEX
    Explanations

    parts of words

    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
    麂
    0.48
     veteran
    0.44
     Shrine
    0.43
     Slaughter
    0.43
    和
    0.42
    档
    0.42
     Tibetan
    0.41
     Freed
    0.41
     Kashmiri
    0.41
     thêm
    0.40
    POSITIVE LOGITS
    organisms
    0.46
    dessä
    0.43
    흩
    0.41
     pierws
    0.39
    लॉक
    0.39
    ränkt
    0.39
     多い
    0.39
     dilaksanakan
    0.39
    рыва
    0.39
    posals
    0.39
    Activations Density 0.005%

    No Known Activations