© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77198
    Prev
    Next
    INDEX
    Explanations

    words starting with ret

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

    the neuron detects mentions of “retina” or its related forms (e.g. retinal, retinitis) in text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     rechargeable
    -0.69
    édie
    -0.69
    nesty
    -0.68
     compositions
    -0.68
     oferty
    -0.68
    thenes
    -0.68
    Bromoform
    -0.67
    bcryptjs
    -0.67
     Vander
    -0.67
     Yorkshire
    -0.66
    POSITIVE LOGITS
    Ret
    3.98
     Ret
    3.92
     retina
    3.83
    ret
    3.72
     retinal
    3.47
     ret
    3.39
     Retina
    3.34
     retin
    3.25
     retaliation
    3.09
    RET
    2.92
    Activations Density 0.188%

    No Known Activations