© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9410
    Prev
    Next
    INDEX
    Explanations

    programming and web development concepts

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

    Scandinavian and programming code

    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_40_width_16k_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
    ('.
    0.47
    hydes
    0.40
     مقام
    0.40
    ኝነት
    0.39
     celebrado
    0.39
     luisant
    0.39
     原子
    0.38
    烙
    0.38
    cio
    0.38
     विश्वास
    0.38
    POSITIVE LOGITS
     Sweden
    0.61
     myFunction
    0.58
     Norway
    0.58
    Norway
    0.57
     Norweg
    0.57
     Шве
    0.57
     সুইড
    0.56
    Swedish
    0.56
     Meghna
    0.55
    Volvo
    0.54
    Activations Density 0.005%

    No Known Activations