© 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. 108117
    Prev
    Next
    INDEX
    Explanations

    article followed by descriptor

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

    This neuron detects the “is a …” biographical introduction phrase (e.g. “is a two-time world champion,” “is a coach,” “is a visual artist,” etc.).

    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
    şu
    -1.18
     others
    -1.14
     other
    -1.10
     LIABLE
    -0.99
    ﺓ
    -0.90
    swire
    -0.88
    _()
    -0.87
     IBOutlet
    -0.85
    OTER
    -0.85
    atization
    -0.84
    POSITIVE LOGITS
     lifelong
    1.23
     certified
    1.20
     award
    1.16
     experienced
    1.12
     freelance
    1.11
     born
    1.10
     seasoned
    1.04
     Certified
    1.02
     graduate
    1.00
    Award
    1.00
    Activations Density 0.099%

    No Known Activations