© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4407
    Prev
    Next
    INDEX
    Explanations

    if you'd like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_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
     Roach
    0.73
     endowment
    0.70
    olver
    0.67
    간
    0.67
     Crawford
    0.64
    Behaviour
    0.64
     proton
    0.64
     Endowment
    0.64
     Principles
    0.63
     delaying
    0.63
    POSITIVE LOGITS
    出荷
    0.73
     nødv
    0.66
    梱包
    0.65
     pís
    0.65
     forfait
    0.63
    ⋮
    0.63
    తున్న
    0.63
    おります
    0.63
     итоге
    0.63
     çoğu
    0.63
    Activations Density 0.024%

    No Known Activations