© 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. 31-GEMMASCOPE-2-RES-262K
    7. 24668
    Prev
    Next
    INDEX
    Explanations

    brakes

    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_31_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
     kimia
    0.44
     másik
    0.43
    김
    0.43
    Bitte
    0.43
     김
    0.43
     constructor
    0.42
     സുമിത്ര
    0.42
    или
    0.42
    製
    0.42
    Nicolas
    0.42
    POSITIVE LOGITS
     brakes
    0.47
     Brake
    0.46
    brake
    0.45
    AKES
    0.42
     ಯಾ
    0.40
     discounts
    0.39
     छोड़कर
    0.39
    憉
    0.39
    rafos
    0.39
    iformes
    0.38
    Activations Density 0.008%

    No Known Activations