© 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. 46858
    Prev
    Next
    INDEX
    Explanations

    vehicles and technical terms

    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
    シャ
    0.45
    RadioButton
    0.43
    湳
    0.39
    凄
    0.39
     demoral
    0.38
    (“
    0.37
    ParameterActive
    0.36
     onSubmit
    0.36
     radiation
    0.36
    ایل
    0.36
    POSITIVE LOGITS
     automobil
    0.52
     Buick
    0.47
     Chevrolet
    0.46
     voiture
    0.43
     വാഹന
    0.43
    煲
    0.42
     автомобиль
    0.42
    ยนต์
    0.42
     گاڑی
    0.42
     Plugging
    0.41
    Activations Density 0.001%

    No Known Activations