© 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. 232125
    Prev
    Next
    INDEX
    Explanations

    their children

    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
     austerity
    0.41
     vans
    0.41
     omin
    0.41
     sana
    0.41
     бушлай
    0.41
    秏
    0.41
    agens
    0.40
    ವಾ
    0.40
     smog
    0.40
     potência
    0.40
    POSITIVE LOGITS
     posiad
    0.49
    ጳ
    0.48
     Liên
    0.48
     człon
    0.47
    唇
    0.47
    ্ষ
    0.46
     sirop
    0.46
    对象
    0.46
    李
    0.46
     combining
    0.45
    Activations Density 0.001%

    No Known Activations