© 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. 156294
    Prev
    Next
    INDEX
    Explanations

    territorial aggression

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

    cells, generosity, exception

    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
    ibil
    0.49
    שת
    0.46
    ations
    0.46
    졀
    0.46
    кха
    0.45
    lardan
    0.44
    濛
    0.44
    लिम
    0.44
     suç
    0.43
    釈
    0.43
    POSITIVE LOGITS
    Flat
    0.46
     لکھنے
    0.44
    优雅
    0.43
     lần
    0.43
     управлять
    0.43
     নিয়ন্ত্রণে
    0.42
     వరు
    0.42
    ząd
    0.42
     طبعا
    0.42
     تھے۔
    0.41
    Activations Density 0.001%

    No Known Activations