© 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. 215966
    Prev
    Next
    INDEX
    Explanations

    SDK, classes, development

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

    technical and conceptual topics

    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
     一
    0.53
    台
    0.48
    jenje
    0.46
    感
    0.46
    的
    0.44
     モ
    0.43
    防疫
    0.42
     그다
    0.41
     invariant
    0.41
    ップ
    0.40
    POSITIVE LOGITS
     розви
    0.46
    Threat
    0.46
    蹂
    0.46
    Opportunities
    0.46
     Rousse
    0.46
    Europa
    0.46
    Contributions
    0.46
     lézard
    0.45
    Antoine
    0.45
    Alles
    0.45
    Activations Density 0.001%

    No Known Activations