© 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. 152977
    Prev
    Next
    INDEX
    Explanations

    heart, leash, read, meat

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

    models and response

    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
     functionalities
    0.58
     holomorphic
    0.49
     overfitting
    0.48
     umfang
    0.48
    ٿ
    0.46
     logits
    0.46
     outperforms
    0.45
    ंकज
    0.45
     lleva
    0.44
     wichtigsten
    0.44
    POSITIVE LOGITS
    legisl
    0.45
     և
    0.43
     પરંતુ
    0.43
    instit
    0.43
     Совет
    0.43
    綀
    0.43
     فره
    0.42
    秘书
    0.41
     եւ
    0.41
    之间
    0.41
    Activations Density 0.001%

    No Known Activations