© 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. 60341
    Prev
    Next
    INDEX
    Explanations

    from internal

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

    political and geographical entities

    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
    רי
    0.44
    ാ
    0.43
     alcance
    0.42
    γα
    0.42
     zariaden
    0.42
     lijst
    0.41
     chwili
    0.40
     rivel
    0.40
    쵝
    0.40
     controle
    0.39
    POSITIVE LOGITS
     Brexit
    0.50
     cashback
    0.49
     Edinburgh
    0.46
    Brexit
    0.46
     Cashback
    0.46
     বাঁধবেন
    0.42
     انتخاب
    0.42
     избира
    0.41
    सरकार
    0.41
     экономической
    0.41
    Activations Density 0.000%

    No Known Activations