© 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. 5932
    Prev
    Next
    INDEX
    Explanations

    multilingual content

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

    that followed by a word

    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
    5
    0.45
     також
    0.40
     also
    0.39
     myös
    0.39
    6
    0.39
     también
    0.38
    8
    0.38
    4
    0.38
     też
    0.37
     også
    0.37
    POSITIVE LOGITS
     совершенно
    0.36
    全世界
    0.36
     ನಮ್ಮ
    0.35
     現在
    0.35
    
    0.34
    所謂
    0.34
     наша
    0.33
    全新的
    0.33
    ClearedBy
    0.33
     রীতি
    0.33
    Activations Density 0.083%

    No Known Activations