© 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-262K
    7. 136787
    Prev
    Next
    INDEX
    Explanations

    uncontrolled proliferation

    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
     어떻게
    0.41
     dyads
    0.41
    umap
    0.40
     dung
    0.39
     perceptions
    0.38
     INCREASE
    0.37
     staples
    0.37
    :"
    0.37
     adc
    0.36
    如何
    0.36
    POSITIVE LOGITS
     Боль
    0.39
    課題
    0.39
     Thirteen
    0.38
     ചില
    0.38
     ಸಾಕಷ್ಟು
    0.38
     preciso
    0.38
     Viele
    0.38
    <0xB4>
    0.38
     Tauri
    0.38
     Gradually
    0.38
    Activations Density 0.001%

    No Known Activations