© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6145
    Prev
    Next
    INDEX
    Explanations

    district

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

    districts and their types

    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_53_width_65k_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
     Dumping
    0.40
     секу
    0.37
     Diagonal
    0.36
     Dump
    0.36
    𝔰
    0.36
    dataFormat
    0.35
    >)`](
    0.35
     shag
    0.35
     dumped
    0.35
     Dunk
    0.35
    POSITIVE LOGITS
     district
    4.69
    district
    4.47
     District
    4.44
    District
    4.38
     DISTRICT
    4.19
     districts
    4.03
     Districts
    3.89
     distrito
    3.73
     जिला
    3.48
    区
    3.47
    Activations Density 0.152%

    No Known Activations