© 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. 1956
    Prev
    Next
    INDEX
    Explanations

    asking for more details

    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
     harnessing
    1.50
     interplay
    1.50
     Leveraging
    1.49
     Maintaining
    1.48
     leveraging
    1.48
    Computational
    1.48
     outweigh
    1.44
    '];?>
    1.44
     outweighs
    1.44
     outperforms
    1.44
    POSITIVE LOGITS
    例えば
    1.52
     обычно
    1.49
    граф
    1.40
     patru
    1.40
     ordinairement
    1.37
    s
    1.36
    usually
    1.36
    т
    1.35
    :(
    1.33
     pintor
    1.32
    Activations Density 0.228%

    No Known Activations