© 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. 121490
    Prev
    Next
    INDEX
    Explanations

    song as, marketing problem, his two, with controlled

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

    developer descriptions and advice

    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
    กัน
    0.48
    ล
    0.45
    шей
    0.45
    ת
    0.44
    hey
    0.43
    reserv
    0.43
     Sensory
    0.43
    وات
    0.43
    긋
    0.43
    就行
    0.43
    POSITIVE LOGITS
     inclination
    0.47
     itemId
    0.45
     exchanges
    0.45
     ¥
    0.42
     ゼ
    0.41
     Vật
    0.41
     нуля
    0.41
     ソフト
    0.40
     オレンジ
    0.40
     cuyas
    0.40
    Activations Density 0.001%

    No Known Activations