© 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. 51194
    Prev
    Next
    INDEX
    Explanations

    wherever your

    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
    權
    0.44
    MSFont
    0.42
    တိုင်း
    0.41
    Texture
    0.40
    就需要
    0.40
     دماغ
    0.40
    нкү
    0.39
    눔
    0.39
    mbito
    0.38
     বাজে
    0.38
    POSITIVE LOGITS
     यांना
    0.44
     peaking
    0.43
    这个人
    0.41
    жение
    0.41
     EXECUTIVE
    0.41
     DOWN
    0.40
     executive
    0.40
     litros
    0.40
     przygot
    0.39
    лло
    0.39
    Activations Density 0.006%

    No Known Activations