© 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. 8330
    Prev
    Next
    INDEX
    Explanations

    English teaching and proficiency

    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
     bhith
    2.45
    issent
    2.37
    esu
    2.36
     hepatocellular
    2.34
     identidad
    2.31
    iverse
    2.30
    acylglycer
    2.29
     absen
    2.28
    ierend
    2.27
    嶇
    2.27
    POSITIVE LOGITS
    minster
    1.54
    speaking
    1.41
    ิร์
    1.39
    worms
    1.13
     bedste
    1.13
    language
    1.12
    Moderate
    1.11
    worst
    1.10
     sophistic
    1.09
    omans
    1.06
    Activations Density 0.028%

    No Known Activations