© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 11507
    Prev
    Next
    INDEX
    Explanations

    UK government organizations

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

    national agencies and guidance

    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
     rougeâtre
    0.85
     burlap
    0.72
     jaunâtre
    0.71
     computadora
    0.68
     grayish
    0.67
    美國
    0.64
     Amerikaanse
    0.64
     寸
    0.63
    陽
    0.62
     Když
    0.62
    POSITIVE LOGITS
     underpinned
    0.96
     underpin
    0.87
     UK
    0.84
     PwC
    0.75
     statutory
    0.75
     underpinning
    0.74
     HMRC
    0.74
    Wales
    0.72
     scoping
    0.71
    UK
    0.70
    Activations Density 0.140%

    No Known Activations