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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 7769
    Prev
    Next
    INDEX
    Explanations

    generative image models

    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
    ESSAGE
    0.43
    smarty
    0.42
    engage
    0.41
     Soils
    0.41
     вино
    0.40
    libexec
    0.40
    হাম্ম
    0.39
    흡
    0.39
    COUN
    0.39
    achelor
    0.38
    POSITIVE LOGITS
     generative
    1.20
    生成
    1.02
     生成
    0.90
     generator
    0.89
    VAE
    0.89
     GAN
    0.88
     Generator
    0.88
     latent
    0.86
     images
    0.86
    Diffusion
    0.86
    Activations Density 0.182%

    No Known Activations