© 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. 4998
    Prev
    Next
    INDEX
    Explanations

    following `is` or `am`

    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
    по
    2.58
    ست
    2.56
    в
    2.47
    то
    2.46
    см
    2.42
     други
    2.37
     реда
    2.34
    нете
    2.32
     има
    2.31
     впли
    2.30
    POSITIVE LOGITS
     SULF
    1.26
     sulfates
    1.25
    을
    1.21
    으니
    1.20
     더
    1.19
     banter
    1.18
     foils
    1.18
     문의
    1.15
     nhiêu
    1.11
     이곳
    1.11
    Activations Density 0.004%

    No Known Activations