© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 31486
    Prev
    Next
    INDEX
    Explanations

    payment Computing; If is; Evolution your; en isn; orne /; ( ,; Japanese Of; ( ,; A Optional

    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/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     gewährle
    0.49
    鋈
    0.47
    ="))
    0.44
     الذين
    0.43
     TextBox
    0.42
    渶
    0.41
    charCodeAt
    0.41
    于
    0.40
     يع
    0.39
     దాని
    0.38
    POSITIVE LOGITS
     аны
    0.40
    ংকর
    0.36
     zlat
    0.36
    +,
    0.36
    Ill
    0.35
    ensibility
    0.35
     donations
    0.35
    शिष्ट
    0.35
     millennials
    0.35
    Probability
    0.35
    Activations Density 0.001%

    No Known Activations