© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 72787
    Prev
    Next
    INDEX
    Explanations

    concept representation is

    np_acts-logits-general · gemini-2.5-flash-lite

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    هام
    0.48
     opposites
    0.47
     幅
    0.46
     volunt
    0.45
    [(\
    0.45
    們
    0.45
     obstructing
    0.44
     Vaill
    0.44
    媾
    0.43
     તો
    0.42
    POSITIVE LOGITS
    保证
    0.43
     лучших
    0.42
    Creative
    0.40
    प्रयोग
    0.40
    PrivateKey
    0.39
    栾
    0.39
     alloys
    0.38
    लांग
    0.38
    FactoryBean
    0.38
     assembler
    0.38
    Activations Density 0.005%

    No Known Activations