© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203589
    Prev
    Next
    INDEX
    Explanations

    any other, raw material, most traditional, specialized instruction

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

    AI-generated creative content and religious concepts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     করিয়৷
    0.50
     ۱۹
    0.49
     obl
    0.48
    angkalan
    0.44
     mieć
    0.42
    Ⅰ
    0.42
    うる
    0.41
     仮
    0.41
     참
    0.41
     うる
    0.40
    POSITIVE LOGITS
     সিগারে
    0.49
    ᱙
    0.48
     blogging
    0.47
     scrut
    0.46
    ⸩
    0.45
    镳
    0.45
    popupTheme
    0.45
     attendant
    0.44
    essay
    0.44
    िडेट
    0.44
    Activations Density 0.000%

    No Known Activations