© 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. 128287
    Prev
    Next
    INDEX
    Explanations

    risks, duty, failure

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

    China, resentment, suits, Wright

    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
     Pond
    0.48
     দ্রব
    0.45
     mjes
    0.45
     learned
    0.45
    事情
    0.44
     Blessed
    0.44
     அவர்களிடம்
    0.43
    奭
    0.43
     البلد
    0.42
     arise
    0.42
    POSITIVE LOGITS
    èves
    0.47
    澳門
    0.46
    ق
    0.45
    ur
    0.44
    gpu
    0.44
     ENV
    0.44
    ୬
    0.43
    გენ
    0.43
    Regulation
    0.43
    جے
    0.43
    Activations Density 0.000%

    No Known Activations