© 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. 109046
    Prev
    Next
    INDEX
    Explanations

    Lerner | Lerman | Lawyer | Lerios

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

    The neuron consistently flags tokens containing the character sequence “ler” as part of people’s names.

    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
    ogni
    -0.82
     lặng
    -0.80
    Spot
    -0.76
    ſta
    -0.76
    仓库
    -0.76
    нология
    -0.76
     graciosos
    -0.75
     penas
    -0.75
    vatten
    -0.75
    Trevor
    -0.75
    POSITIVE LOGITS
     Lear
    0.79
    ''''
    0.76
    Ler
    0.76
    Learner
    0.75
    Sexuality
    0.75
    lauf
    0.74
     NPT
    0.72
     Ler
    0.71
    ứa
    0.69
     Abba
    0.69
    Activations Density 0.024%

    No Known Activations