© 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. 14299
    Prev
    Next
    INDEX
    Explanations

    Eddie followed by a name

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

    The neuron activates on occurrences of the word “reflector.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    In
    -3.47
     
    -3.30
    𐄁
    -2.95
    I
    -2.61
    すごく
    -2.53
     It
    -2.47
    在自己
    -2.44
     ‘‘
    -2.41
     técn
    -2.39
     coveted
    -2.39
    POSITIVE LOGITS
    复制代码
    2.95
    栳
    2.92
     {
    2.63
     jenner
    2.59
     itſelf
    2.55
     }?>
    2.38
     garcia
    2.34
     ถ้า
    2.33
     padx
    2.31
    飒
    2.31
    Activations Density 0.005%

    No Known Activations