© 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. 5204
    Prev
    Next
    INDEX
    Explanations

    simply defining

    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
    leftChild
    1.34
     Geißler
    1.32
     mesmas
    1.25
     Vou
    1.23
    ✘
    1.22
    Ⲕ
    1.21
     Vitor
    1.21
    ジュニア
    1.20
    InitStructure
    1.20
     JL
    1.19
    POSITIVE LOGITS
     a
    1.83
     something
    1.72
     downright
    1.66
    あくまで
    1.57
     truly
    1.55
     actually
    1.53
     simply
    1.51
     fundamentally
    1.50
     just
    1.48
    むしろ
    1.48
    Activations Density 0.224%

    No Known Activations