© 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. 75587
    Prev
    Next
    INDEX
    Explanations

    foreign language text

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

    learn and education contexts

    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
     accepter
    0.48
     عق
    0.47
     matchups
    0.46
    dle
    0.43
     类型
    0.43
    ؤ
    0.41
     indoctr
    0.41
    ielder
    0.40
     volley
    0.40
     stances
    0.40
    POSITIVE LOGITS
    த்திரை
    0.49
     organizada
    0.48
     Daha
    0.48
    ା
    0.48
    Ა
    0.47
    ྒྱ
    0.47
     organizar
    0.46
     toplant
    0.46
    山西
    0.46
     непосредственно
    0.45
    Activations Density 0.000%

    No Known Activations