© 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-16K
    7. 2182
    Prev
    Next
    INDEX
    Explanations

    list items and instructions

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     lousy
    1.72
     sweetest
    1.70
    Cutting
    1.69
    terer
    1.68
     terminator
    1.67
     stunning
    1.66
    cutting
    1.66
    сар
    1.64
     searing
    1.63
    콤
    1.63
    POSITIVE LOGITS
     Yorke
    1.22
     ansvar
    1.12
    ogue
    1.08
     conductas
    1.07
     ansiedad
    1.02
     mappe
    1.01
    nogo
    1.00
    pons
    0.98
    疚
    0.97
    Appendix
    0.96
    Activations Density 0.211%

    No Known Activations