© 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. 63463
    Prev
    Next
    INDEX
    Explanations

    duo

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

    Base64 encoding

    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
     করেছি
    0.42
     گرفته
    0.42
     ቡ
    0.42
     Corporation
    0.41
    اں
    0.41
     পাঠ
    0.41
    Disabled
    0.41
     تک
    0.41
     Supplements
    0.41
     روغن
    0.41
    POSITIVE LOGITS
    m
    0.54
    理想
    0.48
    谛
    0.47
     daz
    0.45
     VX
    0.45
    击
    0.45
    slut
    0.44
    слежи
    0.44
     felices
    0.44
    तौर
    0.44
    Activations Density 0.000%

    No Known Activations