© 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. 29360
    Prev
    Next
    INDEX
    Explanations

    Ankara, Istanbul, Turks

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

    individual characters and elements

    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
     մե
    0.43
     রাজনী
    0.42
     certainement
    0.41
    ភ្ល
    0.41
     ≠
    0.40
    へと
    0.39
    osch
    0.39
    𝐳
    0.39
     নিঃসন্দেহে
    0.38
     ஒவ்வ
    0.38
    POSITIVE LOGITS
    itaea
    0.48
     Ankara
    0.46
    Istanbul
    0.46
     бого
    0.46
    istanbul
    0.45
     Turks
    0.45
     Turkish
    0.45
     मलेशिया
    0.43
    。『
    0.43
     theolog
    0.42
    Activations Density 0.000%

    No Known Activations