© 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. 10-GEMMASCOPE-RES-131K
    7. 61215
    Prev
    Next
    INDEX
    Explanations

    camera and display

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

    The neuron fires on technical hardware feature terms in product specs (e.g. display, camera, video, touchscreen, keyboard).

    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
    </h3>
    -1.51
     metálico
    -1.37
     käytt
    -1.35
    辄
    -1.34
     löytyy
    -1.34
    menina
    -1.27
    谙
    -1.27
    comida
    -1.26
    guantes
    -1.23
     politiker
    -1.22
    POSITIVE LOGITS
    бурга
    1.45
     "-
    1.35
    和你
    1.34
     "
    1.32
     no
    1.27
     ]
    1.19
    )$-
    1.18
     your
    1.16
     airplane
    1.14
    tidine
    1.14
    Activations Density 0.016%

    No Known Activations