© 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. 53-GEMMASCOPE-2-RES-262K
    7. 81490
    Prev
    Next
    INDEX
    Explanations

    arm or ARM

    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
     pronounce
    0.38
    箜
    0.36
    铌
    0.35
    俳
    0.35
     pagination
    0.34
    പ്പിച്ചി
    0.34
     MCD
    0.34
    eleri
    0.33
    簾
    0.33
     გა
    0.33
    POSITIVE LOGITS
     arm
    3.97
    Arm
    3.92
     Arm
    3.78
     ARM
    3.67
    arm
    3.58
    ARM
    3.48
     arms
    3.06
     Arms
    2.86
    arms
    2.80
    臂
    2.77
    Activations Density 0.047%

    No Known Activations