© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 2937
    Prev
    Next
    INDEX
    Explanations

    components and features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     состави
    1.64
     который
    1.58
     אשר
    1.57
    および
    1.52
    ј
    1.50
    ستين
    1.49
     свидетель
    1.48
     також
    1.46
     таксама
    1.46
    ový
    1.46
    POSITIVE LOGITS
     interpersonal
    2.15
     tenths
    2.01
     verbal
    1.90
     painless
    1.89
     macroscopic
    1.87
     `{
    1.86
     mundane
    1.85
     residual
    1.84
     frustration
    1.81
     reproducible
    1.80
    Activations Density 0.333%

    No Known Activations