© 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. 38559
    Prev
    Next
    INDEX
    Explanations

    recommendations or findings

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

    "I" and "We" followed by verbs

    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
    怎樣
    0.46
    FromArray
    0.45
     他
    0.44
     Serr
    0.42
    ميم
    0.41
    我认为
    0.41
     يعمل
    0.41
    Tera
    0.40
     i
    0.40
     erc
    0.40
    POSITIVE LOGITS
     loves
    0.58
     recommandé
    0.48
     recomand
    0.48
     regelmatig
    0.48
     Loves
    0.47
     aici
    0.47
    нг
    0.46
    льні
    0.46
     Artikel
    0.46
     பரிந்து
    0.46
    Activations Density 0.121%

    No Known Activations