© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10350
    Prev
    Next
    INDEX
    Explanations

    immigration reform

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

    pornography, tree care, autistic differences

    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
     phosphorous
    0.55
     Jehova
    0.52
     brillo
    0.50
     oxi
    0.49
     leech
    0.48
     মুজিবর
    0.47
    膣
    0.46
    ্রাস
    0.44
     onyx
    0.44
     anhydride
    0.44
    POSITIVE LOGITS
     करके
    0.46
    gunta
    0.44
    ፖ
    0.42
    coronavirus
    0.42
    رو
    0.41
    existe
    0.41
     profoundly
    0.40
     عنها
    0.39
     माणसा
    0.39
     श्रीकृष्ण
    0.39
    Activations Density 0.590%

    No Known Activations