© 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. 212621
    Prev
    Next
    INDEX
    Explanations

    trash collection, extended warranty, LED matrix

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

    Date numbers domain names MLC

    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
    Об
    0.61
    母
    0.54
    Благо
    0.52
    У
    0.52
    С
    0.51
    Ю
    0.51
    Пре
    0.50
    Ку
    0.49
    لق
    0.48
    Ска
    0.48
    POSITIVE LOGITS
     superhuman
    0.54
     shameless
    0.49
     ढ
    0.48
     sham
    0.46
     מו
    0.45
     применя
    0.45
     sporty
    0.45
     ቲ
    0.45
     служит
    0.45
    ্কা
    0.44
    Activations Density 0.000%

    No Known Activations