© 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. 109259
    Prev
    Next
    INDEX
    Explanations

    Eld with common suffixes

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

    This neuron activates on tokens containing the substring “Eld.”

    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
    BigInteger
    -0.78
    inkov
    -0.78
    DISCUSSION
    -0.76
    GLUT
    -0.76
     UNS
    -0.72
    <0xF4>
    -0.71
     CEC
    -0.71
    OPERATOR
    -0.71
    ſes
    -0.70
     Tbsp
    -0.70
    POSITIVE LOGITS
    ridge
    0.79
    脊
    0.75
    하다
    0.71
     Carta
    0.69
    ソン
    0.69
    accep
    0.68
    otts
    0.67
    BREAKING
    0.67
    TRAVEL
    0.66
    AAS
    0.66
    Activations Density 0.031%

    No Known Activations