© 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. 158659
    Prev
    Next
    INDEX
    Explanations

    stretch out

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

    stretches languidly

    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
    閇
    0.45
    opoulos
    0.45
    нон
    0.43
    differential
    0.41
    穢
    0.41
    publication
    0.41
    Differential
    0.40
    ੨
    0.40
    ференциа
    0.40
    ༢
    0.39
    POSITIVE LOGITS
     assertTrue
    0.42
     বিষ্ণ
    0.41
     TN
    0.40
     Munn
    0.40
     其中
    0.40
    சின
    0.39
    சித்து
    0.39
     Taz
    0.39
     FACT
    0.38
     TM
    0.38
    Activations Density 0.000%

    No Known Activations