© 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. 218514
    Prev
    Next
    INDEX
    Explanations

    dive, Case, relationship, Discover

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

    situation, bits

    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
     التص
    0.48
     Cáceres
    0.48
     zusätzlich
    0.48
     Além
    0.47
     Ін
    0.47
     資
    0.47
     Ин
    0.46
     ла
    0.46
     ніж
    0.46
     Caes
    0.46
    POSITIVE LOGITS
    AGUE
    0.51
    지
    0.49
     coil
    0.47
    নিম্ন
    0.46
    کراچی
    0.45
     mySocket
    0.44
     tangan
    0.44
    ไต
    0.43
    课堂
    0.43
     cumbersome
    0.43
    Activations Density 0.000%

    No Known Activations