© 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. 33183
    Prev
    Next
    INDEX
    Explanations

    fixed, constant, static concepts

    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
     erasure
    0.47
     eraser
    0.42
     Microsc
    0.41
     oficialmente
    0.41
    gments
    0.39
     خفی
    0.39
    模糊
    0.38
    *=
    0.38
     sobra
    0.38
     athletic
    0.37
    POSITIVE LOGITS
     fixed
    1.51
    Fixed
    1.48
    固定
    1.46
     Fixed
    1.38
     ثابت
    1.36
    fixed
    1.34
     固定
    1.34
     unchanging
    1.27
     स्थिर
    1.27
     স্থির
    1.20
    Activations Density 0.200%

    No Known Activations