© 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. 197496
    Prev
    Next
    INDEX
    Explanations

    changing, bargaining, last, dust, insurer

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

    software development tools

    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
     аудио
    0.50
    ча
    0.49
     असतात
    0.47
    ા
    0.47
    Frequently
    0.47
     continuamente
    0.46
    ल
    0.46
    ѐ
    0.45
     регулярно
    0.45
    Waves
    0.45
    POSITIVE LOGITS
     hapless
    0.47
     in
    0.47
     doesn
    0.46
    別人
    0.44
     aig
    0.44
     policeman
    0.43
     heft
    0.43
     അതേ
    0.43
     she
    0.43
     spying
    0.43
    Activations Density 0.002%

    No Known Activations