© 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. 80384
    Prev
    Next
    INDEX
    Explanations

    day that, takeoff from, board, amidst, neighboring countries, hospital in

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

    old, specific, exactly, study

    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
    T
    0.59
    C
    0.53
    F
    0.51
    E
    0.50
    D
    0.50
    टा
    0.48
    EQU
    0.46
    M
    0.45
    EAR
    0.45
    Clinical
    0.45
    POSITIVE LOGITS
     مغربی
    0.51
    fromParams
    0.49
     सीताराम
    0.47
     ကို
    0.46
    靕
    0.46
    ickej
    0.46
    淈
    0.46
     chặn
    0.45
     ทำให้
    0.45
    這裡是
    0.45
    Activations Density 0.000%

    No Known Activations