© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 21219
    Prev
    Next
    INDEX
    Explanations

    me a, me for, me with

    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_16_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
    ↵↵
    0.54
     Collegiate
    0.44
     diaspora
    0.42
     rarity
    0.40
     independent
    0.40
    ori
    0.40
    바로
    0.40
     T
    0.39
     Water
    0.39
     Plas
    0.39
    POSITIVE LOGITS
    प्ताह
    0.55
     Мін
    0.52
     ويك
    0.52
    ztal
    0.51
     എല്ലാ
    0.51
     উত্তোলন
    0.51
    amano
    0.49
     noirâtre
    0.49
     aziende
    0.49
     Тол
    0.48
    Activations Density 0.000%

    No Known Activations