© 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. 40972
    Prev
    Next
    INDEX
    Explanations

    country club

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

    Valentine's Day

    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
    q
    0.53
    ل
    0.48
     earnest
    0.47
    r
    0.47
    l
    0.47
    ল
    0.45
    fed
    0.45
    fa
    0.44
    o
    0.44
    er
    0.44
    POSITIVE LOGITS
    धिकारिक
    0.49
    ध्ये
    0.48
    ğim
    0.48
    袭击
    0.48
    üp
    0.47
    হিংস
    0.46
     gül
    0.46
     HUB
    0.46
     variáveis
    0.46
     नक
    0.46
    Activations Density 0.001%

    No Known Activations