© 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. 6198
    Prev
    Next
    INDEX
    Explanations

    Casey followed by Card/Eye or Diligently followed by engraved

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

    prepping for

    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
    ܣ
    0.45
    erkraut
    0.38
    ವಾದ
    0.38
     Payroll
    0.38
    鷳
    0.37
     CRA
    0.37
     содержимое
    0.36
     वाणी
    0.36
     உடன்
    0.36
     আবেদনের
    0.36
    POSITIVE LOGITS
     assuming
    0.44
     nets
    0.43
     deb
    0.42
    ালের
    0.42
     Stoner
    0.42
    ukun
    0.40
    撸
    0.40
    lab
    0.39
     आव
    0.39
    bong
    0.39
    Activations Density 0.000%

    No Known Activations