© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2557
    Prev
    Next
    INDEX
    Explanations

    ISS after the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wechsler
    0.64
     Klopp
    0.59
     stumpage
    0.59
     Arbor
    0.58
     Valuation
    0.58
     Shibuya
    0.58
    鴉
    0.57
     %>%
    0.57
     Riot
    0.57
     Ribeiro
    0.57
    POSITIVE LOGITS
     astronauts
    2.22
     astronaut
    2.17
     spacecraft
    2.05
     Astronaut
    1.90
    太空
    1.85
     NASA
    1.84
    NASA
    1.83
    astronaut
    1.77
     косми
    1.73
     अंतरिक्ष
    1.72
    Activations Density 0.352%

    No Known Activations