© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 5122
    Prev
    Next
    INDEX
    Explanations

    take effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    hobby
    0.84
     détour
    0.79
     daydream
    0.79
    礼物
    0.77
    donation
    0.76
    献
    0.76
     trovare
    0.75
    采访
    0.75
     Nähe
    0.74
    搵
    0.70
    POSITIVE LOGITS
    生效
    2.30
     εφαρ
    2.22
     berlaku
    2.21
     적용
    2.19
     EFFECT
    2.18
     diterapkan
    2.14
    適用
    2.12
     efecto
    2.05
     Apply
    2.05
     Effect
    2.04
    Activations Density 0.066%

    No Known Activations