© 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. 6278
    Prev
    Next
    INDEX
    Explanations

    to be able to

    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
     peered
    0.45
     risultato
    0.40
    єш
    0.40
     län
    0.40
    utis
    0.40
     両
    0.40
    ারিত
    0.39
     層
    0.39
    চূ
    0.39
    係
    0.39
    POSITIVE LOGITS
    こちらの
    0.39
     accomplish
    0.39
     사랑
    0.38
    Игра
    0.38
     excell
    0.37
     రచ
    0.37
    ॥
    0.37
     turmeric
    0.37
     minimalistic
    0.37
     choline
    0.37
    Activations Density 0.006%

    No Known Activations