© 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. 216421
    Prev
    Next
    INDEX
    Explanations

    cleaning services, directing

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

    data complexity and classification

    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
    Æ
    0.50
     bı
    0.47
    虑
    0.46
    alu
    0.45
    чів
    0.44
    ahu
    0.44
    anday
    0.44
    恐惧
    0.44
    平静
    0.44
     cambiato
    0.43
    POSITIVE LOGITS
     segregated
    0.48
     Pooling
    0.48
     recounting
    0.46
     உத
    0.45
     retelling
    0.45
     pooling
    0.45
    ン
    0.45
     classifying
    0.43
     exchanging
    0.42
     intrans
    0.42
    Activations Density 0.001%

    No Known Activations