© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 10714
    Prev
    Next
    INDEX
    Explanations

    Software principles

    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_40_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
    羵
    0.46
     मांस
    0.42
    Bienvenidos
    0.39
    椪
    0.39
    ക്കാണ്
    0.39
    مث
    0.39
    ኪያ
    0.38
     materiality
    0.38
    䇢
    0.37
    屇
    0.37
    POSITIVE LOGITS
     Contemporary
    0.40
     People
    0.40
     humans
    0.39
     Humans
    0.39
     Los
    0.38
     Mir
    0.38
    現代
    0.37
    人们
    0.36
     modern
    0.36
     Sometimes
    0.36
    Activations Density 0.001%

    No Known Activations