© 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. 135639
    Prev
    Next
    INDEX
    Explanations

    official parking

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

    defense against, language like, offset percentage

    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
    碗
    0.47
    ดิ
    0.41
    ร
    0.40
    í
    0.40
     stripped
    0.40
     કરવાનું
    0.40
    ☎
    0.40
    睪
    0.40
    缠
    0.39
    壷
    0.39
    POSITIVE LOGITS
    jokes
    0.44
     Kauai
    0.44
     Rah
    0.43
     Footer
    0.43
     Alters
    0.43
    Laut
    0.43
     Header
    0.43
     Laut
    0.43
     Queue
    0.42
    ரள
    0.42
    Activations Density 0.000%

    No Known Activations