© 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. 90890
    Prev
    Next
    INDEX
    Explanations

    camera APS-C DSLR

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

    The neuron strongly activates on alphanumeric model identifiers (especially camera and lens model codes).

    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
    рыз
    -0.77
    zeh
    -0.74
     Informa
    -0.74
     Reflex
    -0.72
    дают
    -0.69
    bleu
    -0.69
    犸
    -0.69
    etsy
    -0.68
    CAE
    -0.67
    diğinde
    -0.67
    POSITIVE LOGITS
     mirror
    1.34
    mirror
    1.23
    Mirror
    1.16
    system
    1.05
     système
    1.02
     Mirror
    0.92
     system
    0.92
     SYSTEM
    0.89
     mirrors
    0.87
    macOS
    0.85
    Activations Density 0.016%

    No Known Activations