© 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. 70624
    Prev
    Next
    INDEX
    Explanations

    engineering Bridge, emerging department, benefits provided, secondary settlement, development, recipe

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

    Bluewillow prompts, Daddy Dom, Minho, dingo, Madrid

    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
     nhưng
    0.47
     !=
    0.45
    underline
    0.43
     unhealthy
    0.42
     nanotubes
    0.42
    !=
    0.41
     simplemente
    0.41
    plasma
    0.40
    hw
    0.39
     quartz
    0.38
    POSITIVE LOGITS
    रूप
    0.47
    ਰੇ
    0.45
    ד
    0.44
     )।
    0.43
     его
    0.43
    दोनों
    0.43
     Bezeichnung
    0.43
    рованы
    0.43
    觫
    0.43
     gehören
    0.42
    Activations Density 0.001%

    No Known Activations