© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75641
    Prev
    Next
    INDEX
    Explanations

    cathode ray tube displays

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

    The neuron strongly activates on technical terms related to cathode‐ray‐tube display hardware (e.g. CRT, electron beam, deflection coil, phosphor screen).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     about
    -1.84
     hebben
    -1.40
    ぶつ
    -1.38
     Unglück
    -1.37
    économ
    -1.32
     poleg
    -1.30
    larla
    -1.30
     takich
    -1.27
     such
    -1.22
     katkıda
    -1.21
    POSITIVE LOGITS
     }
    1.38
     technologie
    1.34
    lllll
    1.31
    知名
    1.30
    商品説明
    1.30
     informar
    1.29
     techo
    1.27
     момент
    1.24
     \&
    1.23
     lago
    1.21
    Activations Density 0.133%

    No Known Activations