© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33776
    Prev
    Next
    INDEX
    Explanations

    rea, reac, reat, reap, reag

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

    The neuron is looking for words starting with "rea" such as "Reagan," "reader," "reaction," "real," etc.

    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_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
     тях
    -0.76
     Sheen
    -0.75
     pound
    -0.74
    こちらも
    -0.73
    tructuring
    -0.72
    commons
    -0.72
    logotipo
    -0.71
     丹
    -0.71
     manipulating
    -0.71
     tweaking
    -0.70
    POSITIVE LOGITS
     Rea
    1.59
    Rea
    1.40
     reac
    1.20
     reactiv
    0.94
     REACT
    0.87
    zur
    0.81
     affirm
    0.80
    ®:
    0.79
    читал
    0.78
    Butyl
    0.76
    Activations Density 0.022%

    No Known Activations