© 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. 210050
    Prev
    Next
    INDEX
    Explanations

    file block management

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

    external scene descriptions

    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
     puluh
    0.56
    ഞ്ചി
    0.49
     converters
    0.48
     promptly
    0.48
     võimalik
    0.48
     penjualan
    0.47
    कत
    0.46
    k
    0.46
    կ
    0.46
     mnog
    0.46
    POSITIVE LOGITS
     বাড়ছে
    0.45
    reflection
    0.44
     Appel
    0.44
     रिश्तों
    0.43
    formData
    0.43
     সম্পর্কের
    0.43
    สม
    0.42
     স্ট্র
    0.42
    𝘱
    0.42
    addImage
    0.42
    Activations Density 0.001%

    No Known Activations