© 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. 21799
    Prev
    Next
    INDEX
    Explanations

    writing and personal stories

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

    personal feelings and preferences

    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
    십시오
    0.41
     사항
    0.41
    ಿತು
    0.40
    므로
    0.39
    spicuous
    0.38
    Masukkan
    0.38
    번
    0.37
    чите
    0.37
    마
    0.36
    маш
    0.36
    POSITIVE LOGITS
     myself
    0.61
    我现在
    0.61
    我自己
    0.60
     ഞാന്‍
    0.59
     نعمل
    0.59
     আমার
    0.58
     என்னுடைய
    0.58
    我觉得
    0.58
     väldigt
    0.57
     veldig
    0.55
    Activations Density 0.154%

    No Known Activations