© 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. 31-GEMMASCOPE-2-RES-262K
    7. 79924
    Prev
    Next
    INDEX
    Explanations

    all mankind

    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_31_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
    他们的
    0.50
     उन्होंने
    0.47
     поса
    0.47
     इंस्टॉल
    0.47
    妷
    0.46
    ．
    0.45
    ლა
    0.45
    他们
    0.45
     القد
    0.44
     değiştir
    0.44
    POSITIVE LOGITS
    зів
    0.49
     resource
    0.48
     waste
    0.46
     biomedical
    0.46
     scientific
    0.46
     healthful
    0.46
     subsistence
    0.45
     contributor
    0.45
     participatory
    0.45
     benevolent
    0.45
    Activations Density 0.006%

    No Known Activations