© 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. 117737
    Prev
    Next
    INDEX
    Explanations

    appeared to

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

    Ukraine War

    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
     déterminé
    0.48
     relatif
    0.47
     vraie
    0.46
     fenêtre
    0.46
    സ്ഥ
    0.46
    蕈
    0.46
     contribuer
    0.45
     laiss
    0.44
     endroit
    0.44
     relativa
    0.44
    POSITIVE LOGITS
    内地
    0.51
    marketing
    0.48
    ě
    0.43
    금융
    0.42
    import
    0.42
    ongo
    0.42
    我想
    0.42
     appeared
    0.41
    income
    0.40
     marketing
    0.39
    Activations Density 0.004%

    No Known Activations