© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3410
    Prev
    Next
    INDEX
    Explanations

    image sensor and capturing

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

    The neuron fires on numeric tokens or digit sequences (e.g. version numbers, constants, or any token containing digits).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     Duque
    -0.76
    Só
    -0.74
    ylem
    -0.67
     AUDIO
    -0.65
     установить
    -0.64
    送り
    -0.64
     Rouen
    -0.64
     augen
    -0.63
     monastery
    -0.63
     ان
    -0.63
    POSITIVE LOGITS
     sensor
    0.92
     ISP
    0.89
     Spock
    0.79
    ッポン
    0.76
    veira
    0.75
     Omni
    0.72
     Sensor
    0.72
     captures
    0.71
     Jordi
    0.71
    atomy
    0.71
    Activations Density 0.015%

    No Known Activations