© 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-65K
    7. 64477
    Prev
    Next
    INDEX
    Explanations

    linguistic elements and 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_65k_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
     નોંધ
    0.40
    Thompson
    0.39
     "
    0.38
     বিশ্ব
    0.38
     Thompson
    0.38
    Taylor
    0.38
    apadam
    0.37
    δ
    0.37
    ϖ
    0.37
     ప్రభ
    0.36
    POSITIVE LOGITS
     logiciel
    0.45
     normalen
    0.44
     learnt
    0.43
     öğrenc
    0.42
     deuxième
    0.42
     preferencias
    0.42
     එක
    0.41
     hạnh
    0.41
    ات
    0.40
    箪
    0.40
    Activations Density 0.026%

    No Known Activations