© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 176747
    Prev
    Next
    INDEX
    Explanations

    applicant will

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

    Cambodian English Akbank beyond

    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
    Negative Logits
    หรือ
    0.54
    點
    0.53
     ότι
    0.52
     ഉ
    0.51
     ಅಥವಾ
    0.50
     hoặc
    0.50
     किंवा
    0.49
    📟
    0.49
     effett
    0.49
     Verificar
    0.49
    POSITIVE LOGITS
     physicist
    0.46
    unam
    0.45
     scholar
    0.44
    oyo
    0.43
     biologist
    0.43
     gait
    0.42
    abi
    0.42
    ii
    0.42
    ajana
    0.42
    una
    0.41
    Activations Density 0.001%

    No Known Activations