© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5344
    Prev
    Next
    INDEX
    Explanations

    living and what follows

    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
     wait
    0.55
     वहीं
    0.54
     admittance
    0.54
     pě
    0.54
    ()){
    0.53
    视角
    0.52
     Homemade
    0.50
     listening
    0.50
    奋
    0.50
     admit
    0.50
    POSITIVE LOGITS
    ston
    0.77
    Living
    0.69
    स्टन
    0.65
     proof
    0.63
     Proof
    0.62
    istica
    0.62
    standards
    0.62
    living
    0.61
     Living
    0.59
    STON
    0.59
    Activations Density 0.069%

    No Known Activations