© 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. 110504
    Prev
    Next
    INDEX
    Explanations

    legal and work obligations

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

    not illegal

    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
     زائدا
    0.48
     बिजली
    0.46
    ި
    0.46
     آشنا
    0.45
     kita
    0.45
     мы
    0.45
     इथे
    0.44
     composants
    0.43
     определение
    0.42
     chúng
    0.42
    POSITIVE LOGITS
    doch
    0.46
    得意
    0.44
    trending
    0.44
    냅
    0.43
    roll
    0.43
    dale
    0.43
    Ped
    0.43
    rogate
    0.42
    У
    0.42
    ished
    0.42
    Activations Density 0.001%

    No Known Activations