© 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. 135779
    Prev
    Next
    INDEX
    Explanations

    expand

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

    greater than, lifespan, delete, leverage, essential

    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
     மணியே
    0.46
    uers
    0.46
    ocarcinoma
    0.42
    У
    0.42
    etic
    0.42
    urando
    0.41
    СО
    0.41
    gere
    0.41
     পারিল
    0.41
     स्तर
    0.40
    POSITIVE LOGITS
     Lietuvos
    0.46
     caffe
    0.46
     Hanna
    0.44
    苼
    0.42
    天氣
    0.42
    䈉
    0.42
     caffeine
    0.41
     verfügen
    0.41
    "],
    0.41
     Phòng
    0.41
    Activations Density 0.001%

    No Known Activations