© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 165832
    Prev
    Next
    INDEX
    Explanations

    custom CUDA kernel

    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
     hover
    0.41
    pxy
    0.40
    ccess
    0.39
    cession
    0.39
     biel
    0.38
    avelength
    0.38
     duration
    0.37
    ḗ
    0.37
     points
    0.37
     छत्र
    0.37
    POSITIVE LOGITS
    写
    0.44
    |$,
    0.38
    ﻻ
    0.38
    仲間
    0.37
     getan
    0.37
    レーション
    0.37
    يدا
    0.37
     সুন্দরী
    0.37
    ucionales
    0.36
    Cute
    0.36
    Activations Density 0.000%

    No Known Activations