© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 34391
    Prev
    Next
    INDEX
    Explanations

    masking or mask

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Giles
    0.38
     chord
    0.38
     taf
    0.38
    izzando
    0.37
    sinh
    0.36
     صوب
    0.36
    掾
    0.36
    揣
    0.36
     Miros
    0.35
    吉田
    0.35
    POSITIVE LOGITS
     mask
    3.28
     masks
    3.14
    Mask
    2.95
    mask
    2.91
     Mask
    2.91
     Masks
    2.84
    マスク
    2.78
     masking
    2.66
    masks
    2.64
     máscara
    2.64
    Activations Density 0.007%

    No Known Activations