© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128139
    Prev
    Next
    INDEX
    Explanations

    tracers, trappings, tramadol, trapidil

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

    The neuron detects words with the prefix "tra" such as "tracers", "trappings", "tramadol", and "trabecular".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    羮
    -2.92
    是
    -2.77
    赁
    -2.66
    緇
    -2.64
    n
    -2.55
    谢谢你
    -2.53
    多谢
    -2.48
     είναι
    -2.45
    注意事
    -2.41
    我已经
    -2.39
    POSITIVE LOGITS
    ).
    3.44
    ?
    3.08
    ".
    2.80
    颔
    2.38
     dismay
    2.28
     barring
    2.27
    捶
    2.27
    缄
    2.25
     snag
    2.25
     нескольких
    2.22
    Activations Density 0.004%

    No Known Activations