© 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-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199575
    Prev
    Next
    INDEX
    Explanations

    The neuron detects positive emotional responses after "so"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_width_262k_l0_small_affine
    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
     teachers
    0.42
    私募基金
    0.42
     usare
    0.40
     Teacher
    0.40
     gh
    0.39
     clue
    0.39
    粆
    0.39
    гі
    0.39
     Teachers
    0.39
     dispensers
    0.38
    POSITIVE LOGITS
    设有
    0.40
    打包
    0.40
     актуа
    0.38
    NotFound
    0.37
     확장
    0.36
    ্লি
    0.36
     HAVE
    0.36
    閉
    0.36
     зада
    0.35
    Nic
    0.34
    Activations Density 0.001%

    No Known Activations