© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 133240
    Prev
    Next
    INDEX
    Explanations

    9 banners oxidative stress supplies

    np_acts-logits-general · gemini-2.5-flash-lite

    offensive racial slurs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Forward
    0.48
    망
    0.43
    橋
    0.41
    Moderate
    0.41
    门
    0.41
    Workflow
    0.41
    Oxford
    0.40
    Translated
    0.40
    *
    0.40
    冉
    0.40
    POSITIVE LOGITS
     lashed
    0.47
     obsz
    0.46
     chụp
    0.45
    owania
    0.44
    াবলীর
    0.44
     takich
    0.44
     lashes
    0.44
     இப்படி
    0.44
     சா
    0.43
     admirers
    0.43
    Activations Density 0.000%

    No Known Activations