© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144177
    Prev
    Next
    INDEX
    Explanations

    handling, design, websites, build

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
     antagonism
    0.49
     event
    0.47
     attenuation
    0.46
     media
    0.45
     utterance
    0.45
    ᱲ
    0.45
     absorbance
    0.44
     conclusions
    0.43
     conclus
    0.43
     incidence
    0.43
    POSITIVE LOGITS
     কেবলমাত্র
    0.45
    sson
    0.45
     ①
    0.44
    phine
    0.43
    不到
    0.43
    ખ્ય
    0.43
    विता
    0.42
     सेब
    0.42
     što
    0.41
     જે
    0.41
    Activations Density 0.005%

    No Known Activations