© 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. 53-GEMMASCOPE-2-RES-262K
    4. 65360
    Prev
    Next
    INDEX
    Explanations

    after verbs like 'but' and 'it'

    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_53_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
     मृ
    0.40
    Sey
    0.38
     motorcycl
    0.36
    ារ
    0.36
    ченный
    0.35
    숑
    0.35
     synerg
    0.35
     Moya
    0.35
     Kiy
    0.35
    Moto
    0.34
    POSITIVE LOGITS
     வண்ணப்பூச்சு
    0.44
    neighborhood
    0.41
    browser
    0.40
    notin
    0.40
    으로써
    0.40
    フォルダ
    0.40
    ﺏ
    0.39
    𝔞
    0.39
    جور
    0.39
     pith
    0.39
    Activations Density 0.001%

    No Known Activations