© 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. 12570
    Prev
    Next
    INDEX
    Explanations

    pronoun or name followed by verb

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

    I need to know

    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
    जब
    0.46
     생긴
    0.44
     Đây
    0.43
    ၊
    0.42
     pertenecen
    0.41
     není
    0.40
     不是
    0.40
    श्मा
    0.40
    {},
    0.40
     habite
    0.40
    POSITIVE LOGITS
    would
    0.43
     could
    0.42
    َ
    0.42
    ંત
    0.41
     पाएंगे
    0.40
    could
    0.40
     می‌تواند
    0.40
     கொள்ளலாம்
    0.40
     می‌توان
    0.39
     dapat
    0.38
    Activations Density 0.465%

    No Known Activations