© 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. 239407
    Prev
    Next
    INDEX
    Explanations

    addresses, wiring, manufacturers, postal, school

    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
    ルの
    0.52
     другими
    0.49
     alfabeto
    0.47
     именем
    0.46
    म
    0.45
    வம்
    0.45
     Аб
    0.43
    ultimo
    0.42
     помощью
    0.42
     память
    0.42
    POSITIVE LOGITS
     malef
    0.41
     tights
    0.40
    Facebook
    0.40
     ஏற்பட
    0.40
     hitters
    0.39
    变形
    0.39
     yaşanan
    0.39
    賂
    0.39
     linemen
    0.38
     ವಿರುದ್ಧ
    0.38
    Activations Density 0.000%

    No Known Activations