© 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. 137781
    Prev
    Next
    INDEX
    Explanations

    Australian companies

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

    describing places

    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
     Anwendungen
    0.55
     roja
    0.53
     antwort
    0.50
     عقب
    0.50
     Panels
    0.49
     مقاب
    0.46
     ⭐
    0.46
     grabación
    0.45
     哈
    0.44
     hängt
    0.44
    POSITIVE LOGITS
     geographically
    0.65
     legislature
    0.62
     geographical
    0.62
     forested
    0.57
     settlers
    0.55
     geography
    0.54
     geographic
    0.54
     насе
    0.52
     hilly
    0.51
     wooded
    0.51
    Activations Density 0.001%

    No Known Activations