© 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. 117778
    Prev
    Next
    INDEX
    Explanations

    camera, lens, imaging

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

    The neuron is detecting alphanumeric technical specifications—model names and numeric parameters (e.g. camera or lens model numbers and focal-length figures).

    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
     irgende
    -0.76
    グリ
    -0.75
     jerseys
    -0.74
    شاء
    -0.74
    hk
    -0.70
     IMPROV
    -0.69
    kmäler
    -0.69
     LEONARD
    -0.69
     recib
    -0.67
     permiso
    -0.66
    POSITIVE LOGITS
     interchangeable
    0.98
     imaging
    0.96
     Imaging
    0.91
    Imaging
    0.84
    imaging
    0.82
     GeForce
    0.80
     kei
    0.78
    mout
    0.75
     MON
    0.75
     fotograf
    0.75
    Activations Density 0.050%

    No Known Activations