© 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. 188094
    Prev
    Next
    INDEX
    Explanations

    dates, variety, prophet, hedge

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

    establishing healthy boundaries

    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
     карда
    0.50
     трансформа
    0.48
    何度
    0.45
    ั
    0.45
    пка
    0.45
     מפ
    0.42
    때
    0.42
    ዝና
    0.42
    燜
    0.42
     ликви
    0.42
    POSITIVE LOGITS
     di
    0.48
    um
    0.48
     inició
    0.48
     ermöglichen
    0.47
     politič
    0.46
    etiti
    0.46
     Tian
    0.45
    clim
    0.45
    ('\\
    0.45
     dib
    0.44
    Activations Density 0.001%

    No Known Activations