© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9352
    Prev
    Next
    INDEX
    Explanations

    specifications or data types

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

    This neuron detects photo‐credit labels (e.g. the word “Photography”) in image captions or bylines.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    سة
    0.77
     McCulloch
    0.77
    سپ
    0.76
     GATT
    0.74
     procedural
    0.73
    ﺭ
    0.72
    ির
    0.71
     mechanistic
    0.71
     stab
    0.71
     Задача
    0.70
    POSITIVE LOGITS
    ý
    0.84
    亜
    0.84
    extérieur
    0.82
    }^{
    0.80
    doors
    0.78
    Cabe
    0.77
    corso
    0.76
     fermé
    0.76
    traces
    0.75
    C
    0.75
    Activations Density 0.001%

    No Known Activations