© 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. 116169
    Prev
    Next
    INDEX
    Explanations

    names and pronouns preceding sentence enders

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

    The neuron is keyed to numeric tokens and digit sequences (i.e. any numbers or numeric references).

    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
     Sì
    -0.94
     legendar
    -0.93
     세트
    -0.93
     SignIn
    -0.92
     malta
    -0.90
     this
    -0.90
    Abbiamo
    -0.90
    ۱
    -0.88
     geï
    -0.85
     чёр
    -0.85
    POSITIVE LOGITS
     contact
    1.96
     email
    1.68
    Contact
    1.55
     hobbies
    1.45
    contact
    1.33
     Email
    1.32
     contacting
    1.32
    email
    1.30
     Contact
    1.30
     graduated
    1.26
    Activations Density 0.056%

    No Known Activations