© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92888
    Prev
    Next
    INDEX
    Explanations

    images, copyright, or technical data

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

    The neuron fires on organization or brand names in credits and licensing attributions (e.g. Getty Images, Reliance Entertainment, Facebook Inc.).

    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
    amaan
    -0.69
     caract
    -0.69
    燼
    -0.65
    uluk
    -0.65
    Ell
    -0.65
    MESS
    -0.65
    ยาว
    -0.64
    になっている
    -0.63
     Trial
    -0.63
     remont
    -0.63
    POSITIVE LOGITS
     Dès
    0.77
    HasColumn
    0.75
    Nelson
    0.73
    комо
    0.71
    CAT
    0.71
    etzt
    0.70
     Montmartre
    0.68
    gart
    0.67
     sockets
    0.66
     師
    0.66
    Activations Density 0.088%

    No Known Activations