© 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. 64867
    Prev
    Next
    INDEX
    Explanations

    doi links

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

    The neuron selectively activates on standalone numerical tokens—especially citation elements like volume, page, issue, or DOI numbers.

    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
     gratuit
    -0.92
    Tere
    -0.89
     moe
    -0.88
    ורך
    -0.81
     étrang
    -0.81
     sice
    -0.81
    mdp
    -0.81
    donc
    -0.81
    thansa
    -0.80
    ミリ
    -0.80
    POSITIVE LOGITS
    0
    1.15
     appoint
    0.94
     putting
    0.93
     with
    0.93
     using
    0.84
     pushing
    0.82
     avoid
    0.81
     appointment
    0.81
     bring
    0.79
     pushed
    0.79
    Activations Density 0.036%

    No Known Activations