© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 52720
    Prev
    Next
    INDEX
    Explanations

    programming languages and code snippets

    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_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
    Ada
    0.40
    inados
    0.38
    Sole
    0.38
    Tape
    0.38
     Bata
    0.37
     Baca
    0.37
    朿
    0.36
     不同
    0.36
     Sole
    0.35
    Agu
    0.35
    POSITIVE LOGITS
     manipulate
    0.43
     décide
    0.41
     tiktok
    0.40
    רו
    0.40
    laravel
    0.39
     larval
    0.39
    आत्म
    0.39
     substantiate
    0.39
     उपकरणों
    0.38
     hausse
    0.38
    Activations Density 0.052%

    No Known Activations